Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant's arguments filed 5/14/2026 on page 8 of remarks and arguments have been fully considered but they are not persuasive. Applicant asserts that “With regard to the § 102(a)(1) and § 103 rejections, Applicant traverses on the ground that the collective teachings of Poole, Wang and Redford fail to disclose all of the features of the claims as previously presented, arranged as recited in those claims, and on the further ground that there is no teaching, suggestion or motivation in the Poole, Wang and Redford references to modify their teachings in a manner that would reach the particular claimed arrangements.” Without a particular claim, concept referenced, or other issue with the existing grounds of rejection the argument that the teachings fail to disclose all features of the non-amended original claims is not found convincing based on the existing grounds of rejection provided in the non-final rejection.
Applicant’s arguments, see pages 8 and 9 of arguments and remarks, filed 5/14/2026, with respect to the amended claim 1/15/18 have been fully considered and are persuasive. It was previously stated in the non-final rejection that Wang teaches obtaining probability densities for pixels as it obtains probability densities on 3D voxel information that is directly made into pixels of a 2D image; during the telephonic interview it was discussed whether or not this actually teaches obtaining probability densities for the pixels themselves. It seems that the claim language was amended to account for this specifically, as claim 1 has been amended to recite that probability densities are found “for at least subsets of pixels”. The initial grounds of rejection relied on the reasoning that since the voxel information like color determines the pixel make up, and the voxel info has probability densities identified for it this teaches obtaining probability densities for the pixels themselves. The amended language that the probability density is found “for at least subsets of pixels” overcomes the rejection as the voxel info that Wang finds probability densities for are not “at least” pixels themselves nor subsets of pixels, only the data that will eventually make up pixels. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made in view of Takeshima (Extracting Object Regions Using Locally Estimated Probability Density Functions).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status. The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-6, 10-16, 18, 19, 21-24, are rejected under 35 U.S.C. 103 as being unpatentable over Poole (DREAMFUSION: TEXT-TO-3D USING 2D DIFFUSION) in view of Wang (Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation) and further in view of Takeshima (Extracting Object Regions Using Locally Estimated Probability Density Functions).
Regarding claims 1, 15, 18,
Poole teaches:
An apparatus comprising: at least one processing device comprising a processor coupled to a memory; (Poole 3.2 Text-To-3D Synthesis “3D scenes are optimized on a TPUv4 machine with 4 chips” Note: The mentioned TPU machine is a type of processor designed for AI and ML training, the machine itself contains a number of connected processors and memory units.) the at least one processing device being configured: to extract a set of features from a user prompt using a natural language processing model; (Poole 2.1 How Can We Sample in Parameter Space, Not Pixel Space? “Figure 3: DreamFusion generates 3D objects from a natural language caption” 3.2 Text-To-3D Synthesis “Text prompts often describe canonical views of an object that are not good descriptions when sampling different views. We therefore found it beneficial to append view-dependent text to the provided input text based on the location of the randomly sampled camera. For high elevation angles φcam > 60°, we append “overhead view.” For φcam ≤ 60°, we use a weighted combination of the text embeddings for appending “front view,” “side view,” or “back view” depending on the value of the azimuth angle θcam (see App. A.2 for details). We use the pretrained 64 × 64 base text-to-image model from Saharia et al. (2022). This model was trained on large-scale web-image-text data, and is conditioned on T5-XXL text embeddings” Note: Poole teaches the use of a model which accepts a natural language caption/text as its inputs for processing, teaching the use of a natural language processing model for user prompts. Feature extraction from the user’s text is taught as well, and is referred to by the analogous term of text embedding. Text embedding or word embedding in natural language processing is used to make a computer usable representation of words, allowing a model to understand the words meaning and context within the sentence. Poole gives a clear example of how a feature of the user’s desired image, which angle the image is captured from, is gained from the words text embeddings allowing the model to extract the desired feature from the sentence and implement it.) to initialize a three-dimensional scene reconstruction model utilizing a set of parameters determined based at least in part on the set of features extracted from the user prompt; (
PNG
media_image1.png
540
862
media_image1.png
Greyscale
Poole 1 Introduction “output 3D object or scene… Originally, NeRF was found to work well for “classic” 3D reconstruction tasks: many images of a scene are provided as input to a model, and a NeRF is optimized to recover the geometry of that specific scene, which allows for novel views of that scene from unobserved angles to be synthesized.” Note: In the Figure 3 caption above Poole describes how a machine learning model, a Neural Radiance Field/NeRF, generates 3D objects and scenes from a natural language caption, or prompt. This model, which is described to excel at “3D reconstruction tasks” is the claims “three-dimensional scene reconstruction model”. Poole teaches that the parameters, which include things like volumetric density and color, are initialized in the NeRF and are then tweaked to match the prompt. This can be seen in the Figure 3 image where a prompt describing a peacock outputs a properly colored peacock in the red box labelled NeRF under the albedo(color) example. This shows Poole teaches a 3D scene reconstruction model that is initialized and has a set of parameters based in part on the features from the user prompt.) to generate, utilizing the three-dimensional scene reconstruction model, a set of two-dimensional images of a given scene from two or more different viewpoint perspectives; (Poole 3 The DreamFusion Algorithm “To synthesize a scene from text, we initialize a NeRF-like model with random weights, then repeatedly render views of that NeRF from random camera positions and angles” 3.1 Neural Rendering of a 3D Model “Rendering an image from a NeRF is done by casting a ray for each pixel from a camera’s center of projection through the pixel’s location in the image plane and out into the world. Sampled 3D points µ along each ray are then passed through an MLP, which produces 4 scalar values as output: a volumetric density τ (how opaque the scene geometry at that 3D coordinate is) and an RGB color c. These densities and colors are then alpha-composited from the back of the ray towards the camera, producing the final rendered RGB value for the pixel”
PNG
media_image2.png
412
878
media_image2.png
Greyscale
Note: In the first provided citation Poole teaches that images of the 3D model the NeRF generates are taken from random angles and positions. In the second citation Poole elaborates on the specific method for producing images from the NeRF, rays are cast from the camera and color and density values are computed to render individual pixels in the image. Figure 4 above is provided to clearly show that two or more images from unique camera angles can be produced, in this case 4. As the NeRF is the claims 3D reconstruction model, Poole clearly teaches how a set of two or more images of a given scene can be generated from different perspectives.) to apply an image diffusion model to the generated set of two-dimensional images to generate a refined set of two-dimensional images; to modify the three-dimensional scene reconstruction model based at least in part on the refined set of two-dimensional images; (
PNG
media_image1.png
540
862
media_image1.png
Greyscale
Note: In Figure 3 above and its accompanying description Poole teaches how 2D images of a 3D model generated by a “3D scene reconstruction model”, which we have established is the NeRF, are used for changing the NeRF. Figure 3 details that once the albedo(color) and density parameters are initialized and tuned by the NeRF to resemble the prompt, images of the NeRF are rendered from random camera positions/angles. To update the NeRF parameters, the renderings/images are input into Imagen, a known diffusion model, and 2D diffused images are produced as seen below the blue Imagen box. The 3D object/scene is then modified based on the 2D diffused images, as an output of the diffused images is “backpropagated through the rendering process to update the NeRF MLP parameters”. This is seen in Figure 3 where the diffused images and their information on the right side has an arrow showing they are backpropagated to the NeRF so parameters can be updated. This clearly teaches the claims language of 2D images are provided to a diffusion model to produce diffused, or refined, images, and how the 3D reconstruction model is then modified based on the 2D refined images.) and to utilize the modified three-dimensional scene reconstruction model to generate a three-dimensional representation of the given scene. (3.2 Text-to-3D Synthesis “For each text prompt, we train a randomly initialized NeRF from scratch. Each iteration of DreamFusion optimization performs the following: (1) randomly sample a camera and light, (2) render an image of the NeRF from that camera and shade with the light, (3) compute gradients of the SDS loss with respect to the NeRF parameters, (4) update the NeRF parameters using an optimizer … 4. Optimization. Our 3D scenes are optimized on a TPUv4 machine with 4 chips. Each chip renders a separate view and evaluates the diffusion … compute time is split evenly between rendering the NeRF and evaluating the diffusion model.” Note: The citation above gives an overview of Poole’s method, covering much of what has already been discussed. In the final step 4, which occurs after the image diffusion takes place as described previously, it is explicitly stated that the NeRF/3D scene reconstruction model renders the final scene. When it renders the 3D scene again it does so this time with updated optimized parameters, teaching the claims language that the now modified 3D scene reconstruction model generates a 3D representation of the scene.); wherein modifying the three-dimensional scene reconstruction model based at least in part on the refined set of two-dimensional images comprises: estimating probability densities for the refined set of two-dimensional images (Poole 2.1 and 2, cited below, teaches that the probability density of the diffused/refined images is determined in order to produce a score which it will use to adjust parameters instead of the density itself.) utilizing a density estimation model that takes at least portions of the refined set of two-dimensional images and the user prompt as input to compute probability density (Poole Abstract “We introduce a loss based on probability density distillation that enables the use of a 2D diffusion model as a prior for optimization of a parametric image generator.” Poole 1. Introduction “Our loss is based on probability density distillation, minimizing the KL divergence between a family of Gaussian distribution with shared means based on the forward process of diffusion and the score functions learned by the pretrained diffusion model. The resulting Score Distillation Sampling (SDS) method enables sampling via optimization in differentiable image parameterizations.” 2.1 “Such models can be specified as a differentiable image parameterization (DIP, Mordvintsev et al., 2018), where a differentiable generator g transforms parameters θ to create an image x = g(θ) … We first investigated reusing the diffusion training loss (Eqn. 1) to find modes of the learned conditional density p(x|y) … Intuitively, this loss perturbs x with a random amount of noise corresponding to the timestep t, and estimates an update direction that follows the score function of the diffusion model to move to a higher density region.” 2.1 “We name our sampling approach Score Distillation Sampling (SDS) as it is related to distillation, but uses score functions instead of densities. We refer to it as a sampler because the noise in the variational family q(zt|...) disappears as t → 0 and the mean parameter of the variational distribution g(θ) becomes the sample of interest.” 2 “Our work builds on text-to-image diffusion models that learn φ(zt;t,y) conditioned on text embeddings y” Poole Eq. 4
PNG
media_image3.png
66
862
media_image3.png
Greyscale
Note: Poole teaches that probability density for refined images is obtained by providing a density estimation model the images and the text prompt to find the density of the image given the prompt. Rather than using probability density itself Poole gets a score based on probability density and then computes a loss. As seen from 2.1, Poole teaches that when noise zt is added at time step t the score function’s loss is minimized, this allows it to move to a higher density region. The equation that computes this loss is shown above, it can be seen that pφ(zt;y,t) is used where zt is the image with noise added at timestep t, and y is the text prompt. The pφ() function represents the probability density itself, where it is typically written as p(x|y), where here the probability density is instead of using image x the image x with noise added, zt, is used with text prompt y. Thus, Poole clearly teaches a probability density model, the diffusion model, which accepts the refined 2D images aka the images produced via diffusion and the prompt and produces a probability density. As stated previously, Poole simply uses this probability density to obtain a score, which it then uses to obtain a loss that can be minimized to optimize parameters. Since Poole includes these additional steps, we do not say Poole teaches optimizing the parameters based on the probability densities themselves.)
While Poole teaches finding probability densities for refined 2D images with a probability density estimation model that accepts the refined image and the prompt it does not teach that probability densities are found for pixels of the image, or that the set of parameters of the 3D reconstruction model can be adjusted with the probability densities. The teaching for finding probability density likelihoods and adjusting the set of parameters of a 3D scene reconstruction model based on the probability densities is found in Wang which teaches utilizing a density estimation model that takes at least portions of the refined set of two-dimensional images to compute probability density likelihoods;(Wang 4, cited below, teaches that the probability density of a 2D diffused, or refined, image is known. The model assumes that the probability density of a 3D model made from the 2D image has a proportional probability density to the probability density of the 2D image. It then uses this to obtain a log likelihood of both probability densities, or in other words the probability density likelihoods, seen below in lines (9)-(11) of the screenshot of Wang 4.) and adjusting the set of parameters of the three-dimensional scene reconstruction model based at least in part on the estimated probability densities. (Wang 4. Score Jacobian Chaining for 3D Generation “Let θ denotes the parameters of a 3D asset, e.g., voxel grid of (RGB, τ ) as in Sec. 4.2. Our goal is to model and sample from the distribution p(θ) to generate a 3D scene. In our setting, only a pretrained 2D diffusion model on images p(x) is given… To relate the 2D and 3D distributions p(x) and p(θ), we assume that the probability density of 3D asset θ is proportional to the expected probability densities of its multiview 2D image renderings xπ over camera poses π, i.e.,
PNG
media_image4.png
548
624
media_image4.png
Greyscale
We will next discuss how to compute the 2D score in practice using a pretrained diffusion model.” 4.2 Inverse Rendering on Voxel Radiance Field “We represent a 3D asset θ as a voxel radiance field [6, 54, 62], which is much faster to access and update compared to a vanilla NeRF parameterized by a neural network [34]. The parameters θ consist of a density voxel grid V(density) ∈ R 1×Nx×Ny×Nz and a voxel grid of appearance features V(app) ∈ R c×Nx×Ny×Nz. Conventionally the appearance features are simply the RGB colors and c = 3 … Image rendering is performed independently along a camera ray through each pixel. We cut a camera light ray into equally distanced segments of length d, and at the spatial location corresponding to the beginning of the i-th segment we sample a (RGBi , τi) tuple from the color and density grids using trilinear interpolation.” 2 “Our method does the opposite: we take an image generative model that is already pretrained on large amounts of 2D data and use it to guide the iterative optimization of a 3D asset. Optimization-based generation makes it much slower compared to 3D GANs, but it becomes possible to harness powerful off-the-shelf 2D generative models such as Stable Diffusion [45] for greater content diversity” Note: Wang teaches that the probability density of 2D image views is found and used to estimate the probability density of a 3D model. As seen in the screenshot from Wang 4 above, line (6) shows that the probability density of the 3D model p(θ) is proportional to p(x). This probability density of the 2D diffused image is then used to obtain a gradient of log-likelihood, or probability density likelihoods, for the 3D reconstruction model as seen in (9)-(11) of the screenshot above. Wang 4.2 teaches that the 3D reconstruction model that will reconstruct a 3D model from information obtained from 2D diffused images is a voxel radiance field, a similar type of model to the neural radiance field leveraged by Poole for its 3D reconstruction model. Thus, Wang teaches optimizing the set of parameters for a 3D reconstruction model using the probability density likelihoods obtained from a probability density estimation model.)
It would have been obvious to a person having ordinary skill in the art before the effective filing
date of the claimed invention to modify Poole with Wang where a probability density estimation model that estimates probability density for a refined set of 2D images and their associated prompt computes a probability density likelihood, and uses the probability densities to refine a set of 3D parameters of a 3D reconstruction model.
There are several reasons that would motivate one to do so, Poole already teaches optimizing its set of 3D parameters with a score it obtains from transferring knowledge of the probability densities. Rather than using a score obtained from probability densities as with Poole computation time could be saved by not further computing the score and simply using the probability densities for optimization as taught with Wang.
Neither Wang nor Poole directly state that the probability density estimation that is performed on the diffused/refined images specifically finds the probability density for at least subsets of pixels of the image. Finding probability density for subsets of pixels in an image is taught by Takeshima which teaches estimating probability densities for at least subsets of pixels of the two-dimensional images (Takeshima 1 “The method proposed in this paper estimates a joint probability density function (joint p.d.f.) of position, color, and class (object or background) for determining whether each pixel belongs to an object or not.” 3 “The proposed method estimates the joint p.d.f. locally for each pixel.”
PNG
media_image5.png
682
644
media_image5.png
Greyscale
PNG
media_image6.png
462
620
media_image6.png
Greyscale
Note: Takeshima teaches that the proability density of each individual pixel in an image is found in order to classify them as belonging to an object in the image. Aside from finding the probability densities for pixels, Takeshima teaches a kernal density estimator which finds the probability density for a space in the image. In other words, the KDE finds the probability density of a subset of pixels. As seen in the screenshots provided above an (s+r) dimensional space of pixels has its probability density estimated for it with the KDE. Regardless of whether the claims language refers to finding probability densities for individual pixels in a subset or a single probability density for an entire subset of pixels, Takeshima teaches both cases.)
It would have been obvious to a person having ordinary skill in the art before the effective filing
date of the claimed invention to modify Poole with Takeshima where: a density estimation model that accepts a refined set of 2D images and prompt produces probability density likelihoods and uses the estimated probability densities to adjust the set of parameters in a 3D scene reconstruction model does not simply find the probability densities for the images, but finds them for at least subsets of pixels of the images.
There are several reasons that would motivate one to do so, Poole and Wang are able to optimize the parameters of their 3D scene reconstruction models with what they have learned from just probability densities of the images themselves. It is possible that more detail from the images could be obtained to help further adjust/optimize the parameters if the probability densities are found on a higher level of detail by finding them for pixels or subsets of pixels rather than the entire image.
Regarding claim 2, 16, 19,
Poole teaches:
The apparatus of claim 1 wherein the three-dimensional scene reconstruction model comprises a Neural Radiance Field (NeRF) model configured to take as input a three-dimensional position vector and a two-dimensional viewing direction and output a color and density at each of two or more points of the given scene. (Poole 3.1 Neural Rendering of a 3D Model “NeRF is a technique for neural inverse rendering that consists of a volumetric raytracer and a multilayer perceptron (MLP). Rendering an image from a NeRF is done by casting a ray for each pixel from a camera’s center of projection through the pixel’s location in the image plane and out into the world. Sampled 3D points µ along each ray are then passed through an MLP, which produces 4 scalar values as output: a volumetric density τ (how opaque the scene geometry at that 3D coordinate is) and an RGB color c. These densities and colors are then alpha-composited from the back of the ray towards the camera, producing the final rendered RGB value for the pixel” Note: Poole teaches that from a camera’s center of projection rays are cast onto individual points on the 3D model, and the information describing each point is obtained from them and used to generate a pixel. The information obtained from each visible point is the color and density information, and as many points are hit with rays in the process of making pixels multiple points colors and densities are obtained from the camera.)
Regarding claim 3,
Poole teaches:
The apparatus of claim 2 wherein initializing the three-dimensional scene reconstruction model comprises initializing weights of a neural network that represents a neural radiance field. (Poole 3 The DreamFusion Algorithm “To synthesize a scene from text, we initialize a NeRF-like model with random weights, then repeatedly render views of that NeRF from random camera positions and angles, using these renderings as the input to our score distillation loss function that wraps around Imagen. As we will demonstrate, simple gradient descent with this approach eventually results in a 3D model (parameterized as a NeRF) that resembles the text.” Note: Here Poole explicitly states that we initialize a neural radiance field model, or a NeRF, with weights which results in the construction of a 3D model or scene.)
Regarding claim 4,
Poole teaches:
The apparatus of claim 1 wherein generating the set of two-dimensional images of the given scene from two or more different viewpoint perspectives comprises: selecting the two or more different viewpoint perspectives to capture a range of perspectives of the given scene;(Poole 3.2 Text-to-3D Synthesis and Figure 4 cited previously detail that two or more viewpoint perspectives are used to capture images from different perspectives of a 3D scene.) for each of the two or more different viewpoint perspectives, performing ray tracing through the given scene for a plurality of rays, where a color and density of each of the plurality of rays is computed using the three-dimensional scene reconstruction model; and synthesizing the set of two-dimensional images of the given scene using the plurality of rays. (Poole 3.1 Neural Rendering of a 3D Model “NeRF is a technique for neural inverse rendering that consists of a volumetric raytracer and a multilayer perceptron (MLP). Rendering an image from a NeRF is done by casting a ray for each pixel from a camera’s center of projection through the pixel’s location in the image plane and out into the world. Sampled 3D points µ along each ray are then passed through an MLP, which produces 4 scalar values as output: a volumetric density τ (how opaque the scene geometry at that 3D coordinate is) and an RGB color c. These densities and colors are then alpha-composited from the back of the ray towards the camera, producing the final rendered RGB value for the pixel” Note: Poole here explicitly states that for the 3D points along each ray color and density are computed. Poole states the rays are cast from a camera’s center and the color and density information is used to produce each of the pixels in the image, as it is already taught that we use multiple cameras from multiple angles this teaches that the set of 2D images Poole produces from different perspectives is done using a plurality of rays.)
Regarding claim 5,
Poole teaches:
The apparatus of claim 1 wherein the image diffusion model comprises a denoising diffusion probabilistic model (DDPM). (Poole A.1 Pseudocode For Ancestral Sampling And Out Score Distillation Sampling
PNG
media_image7.png
368
1062
media_image7.png
Greyscale
Note: Here Poole teaches that the output of DDPM is used as an input in the diffusion model, which has already been established to perform image diffusion.)
Regarding claim 6,
Poole teaches:
The apparatus of claim 1 wherein applying the image diffusion model to the generated set of two-dimensional images comprises applying a noise-reduction process to the generated set of two-dimensional images by: inputting the generated set of two-dimensional images to the image diffusion model; predicting noise added at each timestep based at least in part on an output of the image diffusion model; and removing the predicted noise from the generated set of two-dimensional images to generate the refined set of two-dimensional images. (Poole 2 Diffusion Models and Score Distillation Sampling “diffusion models that learn Eφ(zt;t, y) conditioned on text embeddings … We use Eˆand pˆ throughout to denote the guided version of the noise prediction and marginal distribution” 3.2 Text-to-3D Synthesis “Each iteration of DreamFusion optimization performs the following: (1) randomly sample a camera and light, (2) render an image of the NeRF from that camera and shade with the light, (3) compute gradients of the SDS loss with respect to the NeRF parameters” 2.1 How Can We Sample In Parameter Space, Not Pixel Space? “DreamFusion diffuses the rendering and reconstructs it with a (frozen) conditional Imagen model to predict the injected noise Eˆφ(zt|y;t). This contains structure that should improve fidelity, but is high variance. Subtracting the injected noise produces a low variance update direction stopgrad[E^φ − E] that is backpropagated through the rendering process to update the NeRF MLP parameters … We name our sampling approach Score Distillation Sampling (SDS) as it is related to distillation, but uses score functions instead of densities. We refer to it as a sampler because the noise in the variational family q(zt| . . .) disappears as t → 0” 2 Diffusion Models and Score Distillation Sampling “The forward process is typically a Gaussian distribution that transitions from the previous less noisy latent at timestep t to a noisier latent at timestep t + 1.”Note: Here Poole describes that its “renderings” which refers to the 2D images it renders are diffused with a diffusion model. As part of the specific steps of the diffusion model, we predict the noise that will be created/injected in the image. Once we predict the injected noise, we can then subtract it from the diffused rendering to produce a more refined 2D image. We know that noise is found for each individual timestep as the noise obtained is noted to increase with each timestep.)
Regarding claim 10, 21,
Poole teaches:
The apparatus of claim 1 wherein the user prompt comprises a natural language description of a design of a product, and wherein utilizing the modified three-dimensional scene reconstruction model to generate the three-dimensional representation of the given scene comprises generating a three-dimensional representation of a prototype of the product. (Poole 1. Introduction “This work showed that pretrained 2D image-text models may be used for 3D synthesis, though 3D objects produced by this approach tend to lack realism and accuracy … By combining SDS with a NeRF variant tailored to this 3D generation task, DreamFusion generates high-fidelity coherent 3D objects and scenes for a diverse set of user-provided text prompts.” Note: The claim states that its model is capable of generating a 3D representation of a prototype of a product described in a text prompt. As this simply defines a particular type of 3D content to be generated from a text prompt, and Poole’s model is capable of generating high quality coherent 3D objects and scenes from a diverse set of prompts, the use of Poole to generate prototypes for a design is taught.)
Regarding claim 11,
Poole teaches:
The apparatus of claim 1 wherein the user prompt comprises a natural language description of a virtual showroom of one or more products, and wherein utilizing the modified three-dimensional scene reconstruction model to generate the three-dimensional representation of the given scene comprises generating a three-dimensional representation of the one or more products for the virtual showroom. (Poole 1. Introduction states that high quality coherent objects and scenes can be created from diverse user prompts, as protypes for described designs in a “showroom” environment are simply an example of an objects in a scene Poole teaches this claim as well.)
Regarding claims 12, 22,
Poole teaches:
The apparatus of claim 1 wherein the user prompt comprises a natural language description specifying one or more customizations of a product, and wherein utilizing the modified three-dimensional scene reconstruction model to generate the three-dimensional representation of the given scene comprises generating a three-dimensional representation of a customized version of the product based at least in part on the specified one or more customizations. (
PNG
media_image2.png
412
878
media_image2.png
Greyscale
Note: In the example above, Poole details just a few customizations to 3D models that can be made using natural language descriptions. This teaches the claims description of customizing a product with one or more customizations, as Poole shows a single model (a squirrel) can have multiple objects added separately or concurrently (leather jacket and motorcycle, leather jacket and cello), and also make more abstract customizations such as changing the material of the 3D object to appear as wood. As the products of the claim are simply 3D models, Poole teaches the ability to apply one or more customizations to the model of a product.)
Regarding claim 13, 23,
Poole teaches:
The apparatus of claim 1 wherein the user prompt comprises a natural language description of one or more features of a product, and wherein utilizing the modified three-dimensional scene reconstruction model to generate the three-dimensional representation of the given scene comprises generating a three-dimensional representation of a training simulation for the one or more features of the product. (Figure 4, Poole 1. Introduction cited above Note: As generating a 3D representation of a training simulation is ambiguous, we refer to the specifications statement that “an enterprise may subscribe to or otherwise utilize the development platform 110 for generation of three-dimensional (3D) models for use in digital content creation (e.g., in product development, marketing and sales, customization and personalization, training and simulation, enterprise solutions, etc.”. Referring to this definition, making a “3D representation of a training simulation” consists of generating one or more 3D objects that have relevance for training and simulation. As Poole teaches the ability to make coherent high-quality models, regardless of what purpose they may serve for the user, the ability to make 3D objects that could be used for a training simulation is taught.)
Regarding claim 14, 24,
Poole teaches:
The apparatus of claim 1 wherein the user prompt comprises a natural language description of a configuration of an information technology infrastructure environment, and utilizing the modified three-dimensional scene reconstruction model to generate the three-dimensional representation of the given scene comprises generating a three-dimensional representation of the configuration of the information technology infrastructure environment. (Note: As the configuration of an information technology infrastructure environment is said to be describable with a natural language prompt, and Poole teaches the ability to generate high quality coherent 3D objects from natural language prompts, the ability to generate a particular type of 3D content that can be described with a natural language prompt, in this case an information technology infrastructure environment, is taught.)
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over Poole (DREAMFUSION: TEXT-TO-3D USING 2D DIFFUSION) in view of Wang (Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation) in view of Takeshima (Extracting Object Regions Using Locally Estimated Probability Density Functions) and further in view of Redford (US 20230222336 A1).
Regarding claim 9,
Poole teaches:
The apparatus of claim 1 wherein adjusting the set of parameters of the three-dimensional scene reconstruction model comprises utilizing a gradient descent algorithm that utilizes a loss function comprising the estimated probability densities for the refined set of two-dimensional images. (3. The DreamFusion Algorithm “As we will demonstrate, simple gradient descent with this approach eventually results in a 3D model (parameterized as a NeRF) that resembles the text.” 3.2 Text-To-3D Synthesis “3. Diffusion loss with view-dependent conditioning … Given the rendered image and sampled timestep t, we sample noise E and compute the gradient of the NeRF parameters according to Eqn. 3. 4. Optimization … Compute time is split evenly between rendering the NeRF and evaluating the diffusion model” Note: Poole teaches that gradient descent is the method used for creating the initial 3D model, and for determining the 3D model parameters. Gradient descent is used to further edit the parameters based on the refined 2D images as it is taught a gradient of the NeRF parameters is again computed for the images we produce. It is also that the gradient which alters the parameters is in the diffusion loss step as it leverages a loss function to find the parameters. This loss function is described in detail in the previous claim where it is taught that probability density is a key part in the loss function. This teaches a gradient descent algorithm which utilizes a loss function comprising the estimated probability densities for the refined set of 2D images to adjust the parameters of the three-dimensional scene.)
While Poole finds probability densities it does not specify that probability densities for individual pixels of refined 2D images are found, doing so is taught in Wang which teaches estimated probability densities for the pixels of the refined set of two-dimensional images. How Wang teaches this is discussed in the previous claim.
Neither Poole nor Wang teach that the loss function utilized by a gradient descent algorithm comprises a negative log-likelihood of the estimated probability densities. While Wang mentions log-likelihood, it does not mention that it is negative. Doing so is taught in Redford which teaches a gradient descent algorithm that utilizes a loss function comprising a negative log-likelihood of the estimated probability densities (Redford ¶448 “The neural network A00 is trained with stochastic gradient descent (maximum likelihood—using negative log pdf of random variables as the position and extent variables” ¶423 “There exist various neural networks architectures that can be trained to predict a conditional distribution of the form p(e|t), given a sufficient set of example {e,t} pairs. For a simple Gaussian distribution (univariate or multivariate), a log normal or (negative) log PDF loss function A08 can be used.” ¶11 “a normal distribution and Lognormal is a log-normal distribution, chosen as it only has support on the positive reals. This defines a normally distributed probability density centred on the camera coordinates of a point in 3D space.” Note: Redford teaches that its gradient descent algorithm is composed of a likelihood obtained from a negative log probability density function (pdf). This teaches the claims language of a gradient algorithm that uses a loss function that comprises the negative log likelihood of probability densities.)
It would have been obvious to a person having ordinary skill in the art before the effective filing
date of the claimed invention to modify Poole with Wang and further modify them with Redford where the loss function described uses a probability density likelihood, and that likelihood is obtained from a negative log probability density function.
There are several reasons that would motivate one to do so, negative log likelihood functions are useful as they make optimizing the maximum likelihood easy, as to maximize it you need only minimize the negative log likelihood function. Having a straightforward method to output likelihood is just one of the benefits that would motivate someone to combine Poole and Wang with Redford.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALAN GREGORY HAKALA whose telephone number is (571)272-7863. The examiner can normally be reached 8:00am-5:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, King Poon can be reached at (571) 270-0728. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ALAN GREGORY HAKALA/ Examiner, Art Unit 2617 /KING Y POON/Supervisory Patent Examiner, Art Unit 2617
Prosecution Insights