DETAILED ACTION
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 .
Specification
Applicant is reminded of the proper language and format for an abstract of the disclosure.
The abstract should be in narrative form and generally limited to a single paragraph on a separate sheet within the range of 50 to 150 words. The form and legal phraseology often used in patent claims, such as "means" and "said," should be avoided. The abstract should describe the disclosure sufficiently to assist readers in deciding whether there is a need for consulting the full patent text for details.
The language should be clear and concise and should not repeat information given in the title. It should avoid using phrases which can be implied, such as, "The disclosure concerns," "The disclosure defined by this invention," "The disclosure describes," etc.
The abstract of the disclosure is objected to because “Embodiments of the present disclosure …” Correction is required. See MPEP § 608.01(b).
Claim Rejections - 35 USC § 103
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.
Claim(s) 1, 3-6, 8, 9, and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hooge et al., US PGPUB No. 20250292447 A1, hereinafter Hooge, and further in view of Wang et al., WIPO Pub. No. 2024243250 A2, hereinafter Wang.
Regarding claim 1, Hooge discloses at least one processor comprising one or more circuits to implement (Hooge; at least one processor comprising one or more circuits to implement [¶ 0354-0355 and ¶ 0359], as illustrated within Fig. 13; moreover, processing circuitry is configured to execute computer-readable program code instructions [¶ 0361]):
a first network (Hooge; the processor [as addressed above] (configured) to implement a 1st network [¶ 0323-0325], as illustrated within Fig.11; wherein, Fig. 11 illustrates, a network corresponding to data input/retrieval with image encoders (IEs) and further processing the output of the IEs with conditional generative models (CGMs) in which an output is produced; in other words, a network is established by the communication of information between the two or more components/modules; additionally, generation of a synthetic image [¶ 0304], as illustrated within Figs. 9-11), comprising:
a first diffusion model to generate a first voxel grid representative of a three-dimensional (3D) scene and having a first resolution (Hooge; the 1st network [as addressed above] comprises a 1st diffusion model (i.e. IE and CGM) to generate a 1st voxel grid representative of a 3D scene and having a 1st resolution [¶ 0323-0324], as illustrated within Fig. 11; wherein, the image embeddings (corresponding to a grid representative a scene and having a resolution) can be used as condition for image reconstruction [¶ 0276] and can be as a single image embedding [¶ 0287-0289], as illustrated within Figs. 3-8; wherein, the image data corresponds to a 3D scene [¶ 0093-0094], voxel data [¶ 0095], and implicitly has a resolution given its an image), the first diffusion model being conditioned using at least one input image (Hooge; the 1st diffusion model (i.e. IE and CGM) [as addressed above] being conditioned using at least one input image (i.e. new image, first image embedding, and/or first noisy data) [¶ 0323-0324], as illustrated within Fig. 11; still further, conditional generative model [¶ 0156-0159] based on using input images [¶ 0171-0176]);
a second diffusion model to generate a second voxel grid representative of the 3D scene and having a second resolution (Hooge; the 1st network [as addressed above] comprises a 2nd diffusion model (i.e. another IE and CGM) to generate a 2nd voxel grid representative of the 3D scene and having a 2nd resolution [¶ 0323-0325], as illustrated within Fig. 11; such that a 2nd diffusion model is similar to which was addressed regarding the 1st diffusion model); and
compose a novel view of the 3D scene based at least in part on one or more Gaussian attributes (Hooge; compose a novel view of the 3D scene based at least in part on one or more Gaussian attributes (corresponding to noise, Gaussian distribution) [¶ 0077 and ¶ 0326-0328]; moreover, Gaussian distribution [¶ 0160-0162]).
Hooge fails to disclose the second diffusion model being conditioned using the first voxel grid; and
a second network to:
predict one or more Gaussian attributes within one or more voxels of the second voxel grid;
determine a representation of a distant portion of the 3D scene using the at least one input image; and
compose a novel view of the 3D scene based at least in part on the one or more Gaussian attributes and the representation of a distant portion of the 3D scene.
However, Wang teaches a first network (Wang; a 1st network corresponding to projection domain and/or image domain [Page 3, lines 22- 28 and Page 4, lines 12-15]), comprising:
a first diffusion model to generate a first voxel grid representative of a three-dimensional (3D) scene and having a first resolution (Wang; a 1st diffusion model (i.e. DDPM, forward diffusion process) to generate a 1st voxel grid (i.e. sub-volumes) representative of a 3D scene and having a 1st resolution [Page 3, lines 14-31 and Page 5, lines 8-21], as illustrated within Fig. 1; even further, resolution corresponds to image and noise ratios [Col. 4, lines 6-11]; additionally, a pipeline comprising one or more models [Page 6, lines 11-20], as illustrated within Fig. 2), the first diffusion model being conditioned using at least one input image (Wang; the 1st diffusion model [as addressed above] being conditioned using at least one input image (data y and/or data z) [Page 5, lines 8-21], as illustrated within Fig. 1);
a second diffusion model to generate a second voxel grid representative of the 3D scene and having a second resolution (Wang; a 2nd diffusion model (i.e. DDPM, reverse diffusion process) to generate a 2nd voxel grid (i.e. sub-volumes, or reverse sub-volumes) representative of the 3D scene and having a 2nd resolution [Page 3, lines 14-31 and Page 5, line 22 to Page 6, line 3], as illustrated within Fig. 1; still further, another resolution corresponds to image and noise ratios in a reverse direction [Col. 4, lines 6-11]; additionally, DDPM in an image domain [Page 6, lines 4-10 and Page 7, lines 10-17] and configurations of two DDPMs (e.g. DDPM-P and DDPM-I) within a pipeline [Page 6, lines 11-20], as illustrated within Fig. 2), the second diffusion model being conditioned using the first voxel grid (Wang; the 2nd diffusion model [as addressed above] being conditioned using the 1st voxel grid (associated with the forward diffusion) [Page 5, line 22 to Page 6, line 4]); and
a second network (Wang; a 2nd network (i.e. parallel DDPM, projection domain and/or image domain) [Page 4, lines 12-24]) to:
predict one or more Gaussian attributes within one or more voxels of the second voxel grid (Wang; predict one or more Gaussian attributes (corresponding noise, associated with Gaussian distribution) within one or more voxels of the 2nd voxel grid (i.e. sub-volumes, or reverse sub-volumes) [Page 5, line 10 to Page 6, line 3]);
determine a representation of a distant portion of the 3D scene using the at least one input image (Wang; determine a representation (i.e. sparse-view) of a distant portion (corresponding to data z) of the 3D scene using the at least one input image [Col. 5, lines 3-10 and Col. 5, line 25 to Col. 6 line 3], as illustrated within Fig. 1; moreover, a representative distance of a scene corresponds to the Z data); and
compose a novel view of the 3D scene based at least in part on the one or more Gaussian attributes and the representation of a distant portion of the 3D scene (Wang; compose a novel view (i.e. complete high-quality image volume) of the 3D scene [Page 6, lines 10-28] based at least in part on the one or more Gaussian attributes (corresponding noise, associated with Gaussian distribution) and the representation of a distant portion (corresponding to z data) of the 3D scene [Page 5, line 8 to Page 6, line 9]).
Hooge and Wang are considered to be analogous art because both pertain to generating and/or managing data in relation with media manipulation and/or data extraction, wherein one or more computerized units are utilized in order to produce a visualization.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge, to incorporate a first network, comprising: a first diffusion model to generate a first voxel grid representative of a three-dimensional (3D) scene and having a first resolution, the first diffusion model being conditioned using at least one input image; a second diffusion model to generate a second voxel grid representative of the 3D scene and having a second resolution, the second diffusion model being conditioned using the first voxel grid; and a second network to: predict one or more Gaussian attributes within one or more voxels of the second voxel grid; determine a representation of a distant portion of the 3D scene using the at least one input image; and compose a novel view of the 3D scene based at least in part on the one or more Gaussian attributes and the representation of a distant portion of the 3D scene (as taught by Wang), in order to provide improved imaging that uses techniques to reduce or eliminate artifacts (Wang; [Page 2, lines 21-32]).
Regarding claim 3, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein each of the first diffusion model or the second diffusion model comprises a voxel latent diffusion model (Hooge; each of the 1st diffusion model or the 2nd diffusion model [as addressed within the parent claim(s)] comprises a voxel latent diffusion model [¶ 0166 and ¶ 0248]).
Wang further teaches each of the first diffusion model or the second diffusion model comprises a voxel latent diffusion model (Wang; each of the 1st diffusion model or the 2nd diffusion model [as addressed within the parent claim(s)] comprises a voxel latent diffusion model [Page 4, lines 6-25]; wherein, the aspect of voxel is addressed within the parent claim(s)); and
the first diffusion model and the second diffusion model are a same model (Wang; the 1st diffusion model and the 2nd diffusion model [as addressed above] are a same model (i.e. DDPM) [Page 5, line 8 to Page 6, line 9]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Wang, to incorporate each of the first diffusion model or the second diffusion model comprises a voxel latent diffusion model; and the first diffusion model and the second diffusion model are a same model (as taught by Wang), in order to provide improved imaging that uses techniques to reduce or eliminate artifacts (Wang; [Page 2, lines 21-32]).
Regarding claim 4, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein the first diffusion model is conditioned on a three dimensional (3D) representation of the at least one input image (Hooge; the 1st diffusion model [as addressed within parent claim(s)] is conditioned on a 3D representation of the at least one input image [¶ 0324-0325]; moreover, at least one image embedding correlates as a condition [¶ 0287 and ¶ 0300-0301] in relation with a CGM [¶ 0158-0159]; wherein, image data corresponds to any dimensional (e.g. 3D) [¶ 0093]).
Regarding claim 5, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein the 3D representation of the at least one input image comprises at least one input feature cube (Wang; wherein the 3D representation of the at least one input image [as addressed within the parent claim(s)] comprises at least one input feature cube [Page 9, lines 27-34]; additionally, the sub-volumes representing a imaged volume embodies the form of one or more cubes [Page 5, lines 8-21 and Page 6, lines 4-9], as illustrated within Fig. 1; wherein, Fig. 1 illustrates, multiple cubes corresponding to y and/or x sub-volumes; still further, sub-volumes correspond to cubes/cubic formed of data [Page 6, lines 10-29], as illustrated within Fig. 2).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Wang, to incorporate the 3D representation of the at least one input image comprises at least one input feature cube (as taught by Wang), in order to provide improved imaging that uses techniques to reduce or eliminate artifacts (Wang; [Page 2, lines 21-32]).
Regarding claim 6, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein the first network is a generative geometry network to determine the 3D representation of the scene from the at least one input image (Hooge; the 1st network [as addressed within the parent claim(s)] is a generative geometry network to determine the 3D representation of the scene from the at least one input image [¶ 0188-0189 and ¶ 0323-0325]) by:
extracting one or more features from the at least one input image (Hooge; extracting one or more features (associated with embeddings) from the at least one input image (using an encoder) [¶ 0189 and ¶ 0323-0325]); and
unprojecting the one or more extracted features into the 3D representation (Hooge; unprojecting (corresponding to encoding) the one or more extracted features (associated with embeddings) into the 3D representation [¶ 0323-0325], as illustrated within Fig. 11; wherein, the embeddings can be formed into a combined embedding [¶ 0312-0314 and ¶ 0316]).
Regarding claim 8, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein a first noise and a first condition corresponding to the at least one input image are encoded into the first diffusion model (Hooge; a 1st noise and a 1st condition corresponding to the at least one input image are encoded into the 1st diffusion model [¶ 0323-0324], as illustrated within Fig. 11), which in response outputs the first voxel grid (Hooge; which (is) in response outputs the 1st voxel grid [¶ 0323-0324], as illustrated within Fig. 11); and
a second noise and a second condition comprising the first voxel grid are encoded into the second diffusion model (Hooge; a 2nd noise and a 2nd condition are encoded into the 2nd diffusion model [¶ 0323-0325], as illustrated within Fig. 11), which in response outputs the second voxel grid (Hooge; which (is) in response outputs the 2nd voxel grid [¶ 0323-0324], as illustrated within Fig. 11).
Wang further teaches a second noise and a second condition comprising the first voxel grid are encoded into the second diffusion model (Wang; a 2nd noise and a 2nd condition comprising the 1st voxel grid (i.e. sub-volumes, or forward sub-volumes) are encoded into the 2nd diffusion model (i.e. DDPM, reverse diffusion process) [Page 3, lines 14-31 and Page 5, line 22 to Page 6, line 3], as illustrated within Fig. 1; additionally, DDPM in an image domain [Page 6, lines 4-10 and Page 7, lines 10-17] and configurations of two DDPMs (e.g. DDPM-P and DDPM-I) within a pipeline [Page 6, lines 11-20], as illustrated within Fig. 2), which in response outputs the second voxel grid (Wang; which (is) in response outputs the 2nd voxel grid (i.e. sub-volumes, or reverse sub-volumes) [Page 5, line 10 to Page 6, line 3]).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Wang, to incorporate a second noise and a second condition comprising the first voxel grid are encoded into the second diffusion model, which in response outputs the second voxel grid (as taught by Wang), in order to provide improved imaging that uses techniques to reduce or eliminate artifacts (Wang; [Page 2, lines 21-32]).
Regarding claim 9, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein at least one of the one or more Gaussian attributes (Wang; at least one of the one or more Gaussian attributes (corresponding noise, associated with Gaussian distribution) [as addressed within the parent claim(s)]) comprises at least one of:
a position, a rotation, a scaling, an opacity, a color of a voxel (Wang; the Gaussian attributes (corresponding noise, associated with Gaussian distribution) [as addressed above] comprises an opacity of a voxel [Page 5, line 10 to Page 6, line 3], as illustrated within Fig. 1; in other words, the noise affects the opacity of the sub-volume).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Wang, to incorporate at least one of the one or more Gaussian attributes comprises at least one of: a position, a rotation, a scaling, an opacity, a color of a voxel (as taught by Wang), in order to provide improved imaging that uses techniques to reduce or eliminate artifacts (Wang; [Page 2, lines 21-32]).
Regarding claim 16, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein the one or more processors (Hooge; the one or more processors [as addressed within the parent claim(s)]) are comprised in at least one of:
a control system for an autonomous or semi-autonomous machine;
a perception system for an autonomous or semi-autonomous machine;
a system implemented using a robot;
an aerial system;
a medical system (Hooge; the one or more processors [as addressed within the parent claim(s)] are comprised a medical system [¶ 0076-0078]);
a boating system;
a smart area monitoring system;
a system for performing deep learning operations;
a system for performing simulation operations;
a system for generating or presenting virtual reality (VR) content, augmented reality (AR) content, or mixed reality (MR) content;
a system for performing digital twin operations;
a system implemented using an edge device;
a system incorporating one or more virtual machines (VMs);
a system for generating synthetic data;
a system implemented at least partially in a data center;
a system for performing conversational artificial intelligence (AI) operations;
a system for performing generative AI operations;
a system implementing language models;
a system implementing vision language models (VLMs);
a system implementing large language models (LLMs);
a system implementing multi-modal language models;
a system for hosting one or more real-time streaming applications;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets; or
a system implemented at least partially using cloud computing resources
Claim(s) 2 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hooge in view of Wang as applied to claim(s) 1 above, and further in view of Guizillini et al., US PGPUB No. 20220301206 A1, hereinafter Guizilini.
Regarding claim 2, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein the at least one input image comprises a plurality of images of a scene from a plurality of camera poses (Hooge; the at least one input image [as addressed within the parent claim(s)] comprises a plurality of images of a scene [¶ 0112-0113] from an implicit plurality of camera poses (given the imaging hardware are known to one of ordinary skill in the art) [¶ 0093-0095]).
Hooge as modified by Wang fails to disclose wherein the plurality of images are non-overlapping.
However, Guizilini teaches the at least one input image comprises a plurality of images of a scene from a plurality of camera poses (Guizilini; the at least one input image comprises a plurality of images of a scene from a plurality of camera poses [¶ 0027-0028]), wherein the plurality of images are non-overlapping (Guizilini; the plurality of images are non-overlapping [¶ 0058]).
Hooge in view of Wang and Guizilini are considered to be analogous art because they pertain to generating and/or managing data in relation with media manipulation and/or data extraction, wherein one or more computerized units are utilized in order to produce a visualization.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Wang, to incorporate the at least one input image comprises a plurality of images of a scene from a plurality of camera poses, wherein the plurality of images are non-overlapping (as taught by Guizilini), in order to provide an improved accuracy for reconstructing structure of a scene (Guizilini; [¶ 0023-0024]).
.
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hooge in view of Wang, and further in view of Radwan et al., US PGPUB No. 20240273811 A1, hereinafter Radwan.
Regarding claim 15, Hooge in view of Wang further discloses the at least one processor of claim 1, wherein the one or more circuits (Hooge; wherein the one or more circuits [as addressed within the parent claim(s)]).
Hooge as modified by Wang fails to disclose a Generative Adversarial Network (GAN) to output a refined image using the novel view as input.
However, Radwan teaches wherein the one or more circuits are further to implement a Generative Adversarial Network (GAN) to output a refined image using the novel view as input (Radwan; the one or more circuits are further to implement a GAN to output a refined image using the novel view as input [¶ 0037 and ¶ 0041]).
Hooge in view of Wang and Radwan are considered to be analogous art because they pertain to generating and/or managing data in relation with media manipulation and/or data extraction, wherein one or more computerized units are utilized in order to produce a visualization.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Wang, to incorporate wherein the one or more circuits are further to implement a Generative Adversarial Network (GAN) to output a refined image using the novel view as input (as taught by Radwan), in order to provide an improved image generation with mitigating and/or reducing artifacts (Radwan; [¶ 0003-0004]).
Claim(s) 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hooge in view of Wang, and further in view of Montero, JR. et al., US PGPUB No. 20250166311 A1, hereinafter Montero.
Regarding claim 17, the rejection of claim 17 is addressed within the rejection of claim 1, due to the similarities claim 17 and claim 1 share, therefore refer to the rejection of claim 1 regarding the rejection of claim 17. Although, claim 17 and claim 1 may not be identical, they are considerably comparable or substantially equivalent given their overlapping subject matter. However, the subject matter/limitations not addressed by claim 1 is/are addressed below.
Hooge fails to disclose determine a representation of a portion of the 3D scene corresponding to a sky using the at least one input image.
However, Montero teaches determine a representation of a portion of the 3D scene corresponding to a sky using the at least one input image (Montero; determine a representation of a portion of the 3D scene corresponding to a sky using the at least one input image [¶ 0164-0166]; moreover, foreground and background modeling [¶ 0163], as illustrated within Fig. 13).
Hooge and Montero are considered to be analogous art because both pertain to generating and/or managing data in relation with media manipulation and/or data extraction, wherein one or more computerized units are utilized in order to produce a visualization.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge, to incorporate determine a representation of a portion of the 3D scene corresponding to a sky using the at least one input image (as taught by Montero), in order to provide an improved mixed reality environment of virtual and real space that allow for user immersion (Montero; [¶ 0002 and ¶ 0019-0020]).
Claim(s) 18 is/are rejected under 35 U.S.C. 103 as being unpatentable Hooge, in view of Ntavelis et al., US PGPUB. No. 20240420407 A1, hereinafter Ntavelis, and further in view of Sun et al., US PGPUB. No. 20260080511 A1, hereinafter Sun.
Regarding claim 18, Hooge discloses at least one processor comprising one or more circuits (Hooge; at least one processor comprising one or more circuits [¶ 0354-0355 and ¶ 0359], as illustrated within Fig. 13; moreover, processing circuitry is configured to execute computer-readable program code instructions [¶ 0361]) to:
update at least one Variational Autoencoder (VAE) to learn a latent space over a sparse voxel hierarchy (Hooge; the processor [as addressed above] (configured) to update at least one encoder and/or GCM to learn a latent space over a sparse voxel hierarchy (i.e. embeddings) [¶ 0276, ¶ 0286, and ¶ 0323-0324], as illustrated within Fig. 5; wherein diffusion models correspond to VAE and can be a latent diffusion model [¶ 0165-0166 and ¶ 0196-0198] as well as updated by way of training [¶ 0151-0155]), the sparse voxel hierarchy comprising a first voxel grid having a first resolution and a second voxel grid having a second resolution generated using the at least one VAE (Hooge; the sparse voxel hierarchy (i.e. embeddings) comprising a 1st voxel grid having a 1st resolution and a 2nd voxel grid having a 2nd resolution generated using the at least one encoder and/or GCM [¶ 0323-0325], as illustrated within Fig. 11; wherein, the image data corresponds to voxel data [¶ 0095] and implicitly has a resolution given its an image; and wherein, diffusion models correspond to VAE [as addressed above]);
add noisy to the second voxel grid (Hooge; add noisy to the 2nd voxel grid [¶ 0324-0325]; moreover, noising model [¶ 0161-0164]; wherein, diffusion model may include Markov chains at the noising model and/or denoising model [id.]); and
update at least one diffusion model conditioned on three-dimensional (3D) data associated with two-dimensional (2D) images (Hooge; update at least one diffusion model (i.e. IE and CGM) conditioned on 3D data associated with 2D images (i.e. new image, first image embedding, and/or first noisy data) [¶ 0323-0324], as illustrated within Fig. 11; still further, conditional generative model [¶ 0156-0159] based on using input images [¶ 0171-0176] and wherein, image data corresponds to any dimensional [¶ 0093]).
Hooge fails to disclose the second resolution is greater than the first resolution; and
semantic logit prediction.
However, Ntavelis teaches the second resolution is greater than the first resolution (Ntavelis; the 2nd resolution is greater than the 1st resolution [¶ 0042 and ¶ 0069-0070]).
Hooge and Ntavelis are considered to be analogous art because both pertain to generating and/or managing data in relation with media manipulation and/or data extraction, wherein one or more computerized units are utilized in order to produce a visualization.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge, to incorporate the second resolution is greater than the first resolution (as taught by Ntavelis), in order to provide an improved mixed reality environment of virtual and real space that allow for user immersion (Ntavelis; [¶ 0002 and ¶ 0019-0020]).
Hooge as modified by Ntavelis fails to disclose semantic logit prediction.
However, Sun teaches semantic logit prediction (Sun; semantic logit prediction [¶ 0051-0052 and ¶ 0055]).
Hooge and Ntavelis and Sun are considered to be analogous art because they pertain to generating and/or managing data in relation with media manipulation and/or data extraction, wherein one or more computerized units are utilized in order to produce a visualization.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Ntavelis, to incorporate semantic logit prediction (as taught by Sun), in order to provide improved digital imaging that denoises images accurately and efficiently (Sun; [¶ 0001-0004]).
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hooge in view of Ntavelis and Sun as applied to claim(s) 1 above, and further in view of Guizillini et al., US PGPUB No. 20220301206 A1, hereinafter Guizilini.
Regarding claim 20, The at least one processor of claim 18, wherein the 3D data comprises Light Detection and Ranging (LiDAR) data captured on at least one autonomous vehicle on which the 2D images are captured (Guizilini; the 3D data comprises LiDAR data captured on at least one autonomous vehicle on which the 2D images are captured [¶ 0035 and ¶ 0039]).
Hooge in view of Wang and Guizilini are considered to be analogous art because they pertain to generating and/or managing data in relation with media manipulation and/or data extraction, wherein one or more computerized units are utilized in order to produce a visualization.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing of the claimed invention was made to modify Hooge as modified by Wang, to incorporate the at least one input image comprises a plurality of images of a scene from a plurality of camera poses, wherein the plurality of images are non-overlapping (as taught by Guizilini), in order to provide an improved accuracy for reconstructing structure of a scene (Guizilini; [¶ 0023-0024]).
Allowable Subject Matter
Claims 7, 10-14, and 19 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Refer to PTO-892, Notice of Reference Cited for a listing of analogous art.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Charles Lloyd Beard whose telephone number is (571)272-5735. The examiner can normally be reached Monday - Friday, 8:00 AM - 5: 00 PM, alternate Fridays EST.
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, Tammy Goddard can be reached at (571) 272-7773. 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.
CHARLES LLOYD. BEARD
Primary Examiner
Art Unit 2611
/CHARLES L BEARD/ Primary Examiner, Art Unit 2611
Prosecution Insights