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 .
CLAIM INTERPRETATION
The following is a quotation of 35 U.S.C. 112(f):
(f) ELEMENT IN CLAIM FOR A COMBINATION.—An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as "configured to" or "so that"; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: training module (claim 7) and masking module (claim 8).
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
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 of this title, 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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 7-9, 11, 13-20, 22-24 and 28-30, 32 and 34 are rejected under 35 U.S.C. 103 as being unpatentable over Gowri Somanath et al. [US 20190066733 A1] in view of Ricardo Martin Brualla et al. [US 20220398705 A1].
Regarding claim 7, Gowri teaches and/or suggests:
7. (Original) A training system (i.e. FIG. 1 illustrates a computing device employing a space-time view synthesis mechanism according to one embodiment- ¶0004), comprising:
a model (i.e. As discussed with reference to FIG. 2, view synthesis mechanism 110 provides for a novel technique, using deep learning of neural networks, to offer intermediary images to fill in the plane background for a smoother representation of video or image streams to the user using one or more display devices- ¶0067); and
a training module configured to:
construct a first pair of images of at least a first portion of a first human (i.e. each frame may include and offer any number and type of work units, where each work unit may represent a part (e.g., mast of sailboat, forehead of human face) of the image (e.g., sailboat, human face) represented by its corresponding frame- ¶0018) captured at different times; construct a second pair of images of at least a second portion of a second human captured at the same time from different points of view (i.e. a pair of images/frames may be captured by camera(s) 241 as facilitated by detection/capturing logic 201, where this pair of images/frames (e.g., RGB images/frames) is used as an input into a neural network using deep learning approach to obtain an intermediate view to serve as a middle image/frame of the pair of images/frames an output- ¶0047… a series of images and/or frames 301, 303, 305, 307, 309, 311, 313 may be captured or obtained by one or more cameras of a computing device over multiple viewpoints, perspectives, and time to provide a serious of space-time views as presented by images/frames 301-313. For example, images 301, 303, 305, 307 may be taken by multiple cameras at the same time, such as each camera capturing an image of the same object or scene from a select perspective that provides a unique view of the object/scene corresponding to that camera. As illustrated, for example, four cameras may be used to simultaneously capture images of the same object/scene such that the four images 301, 303, 305, 307 correspond to the four cameras- ¶0065, fig. 3A… capturing of multiple images or frames of an object or a scene by one or more cameras associated with one or more computing devices, where images may include space-images taken by multiple cameras at the same time, or time-images taken by a single camera at different points in time, or a combination there of, such as space-time images- ¶0094, fig. 4);
input the first pair of images to the model; and input the second pair of images to the model (i.e. network training logic 211 of FIG. 2 may be used to train main CNN 403 and CNN 405 using various synthesis sequences containing object and camera motions (x, y and z), where these are generated using, for example, common rendering platform, unity, and scenes composed of random shapes and textures- ¶0085… At block 403, the captured images are used as inputs to a neural network (e.g., CNN) having one or more internal trained networks or layers (e.g., PixelFlow, Synthesis, etc.) for performing certain tasks relevant to view synthesis of the input images- ¶0094), wherein the model is configured to:
generate a first reconstructed image of the at least the first portion of the first human based on the first pair of images (i.e. image 345 represents overlapping of frames 1 341 and 2 343 visualizing parallax, while view synthesis mechanism 110 of FIG. 1 is triggered to perform view synthesis using a trained neural network (e.g., CNN) to provide a middle frame, such as frame 347, representing a time-based intermediary view of frames 1 341 and 2 343. For example, frame 1 341 is obtained at time t and frame 2 343 is obtained in time t+1, both in space s, then the displacement/flow map, F, of middle/intermediary frame 347 is represented by: [t+(t+1)]/2 at s- ¶0075, fig. 3D);
generate a second reconstructed image of the at least the second portion of the second human based on the second pair of images (i.e. using view synthesis mechanism 110 of FIG. 1, images 1 321, 2 323 are processed through view synthesis at a neural network to obtain a space-based intermediary view of images 1 321, 2 323. For example, image 325 represents overlapping of images 1 321 and 2 323 visualizing parallax between cameras 1 and 2, while image 327 is a final “middle” image generated through view synthesis and represents the intermediary view of images 1 321, 2 323. For example, image 1 321 is obtained in space s and image 2 323 is obtained in space s+1, both at time t, then the displacement/flow map, F, of middle/intermediary image 327 is represented by: [s+(s+1)]/2 at t- ¶0070, fig. 3B), and
wherein the training module is further configured to selectively adjust one or more parameters of the model (i.e. further comprising network training logic to train the neural network, wherein training includes end-to-end training facilitating access to additional training data if the neural network serving as a main network is segmented into sub-components, wherein the neural network comprises a convolutional neutral network (CNN)- ¶0127) based on:
However, Gowri does not teach explicitly:
a first difference between the at least the first portion of the first human in the first reconstructed image with a first predetermined image including the at least the first portion of the first human; and
a second difference between the at least the second portion of the second human in the second reconstructed image with a second predetermined image including the at least the second portion of the second human.
In the same field of endeavor, Ricardo teaches:
a first difference between the at least the first portion of the first human in the first reconstructed image with a first predetermined image including the at least the first portion of the first human; and
a second difference between the at least the second portion of the second human in the second reconstructed image with a second predetermined image including the at least the second portion of the second human.
(i.e. the neural network is trained based on minimizing an occlusion loss function between the synthesized image generated by the neural network and a ground truth image captured by at least one witness camera- ¶0011… the loss functions 234 can include a reconstruction loss based on a reconstruction difference between a segmented ground truth image mapped to activations of layers in a NN and a segmented predicted image mapped to activations of layers in the NN. The segmented ground truth image may be segmented by a ground truth mask to remove background pixels and the segmented predicted image may be segmented by a predicted mask to remove background pixels. The predicted mask may be predicted based on a combination of both visible light information captured for a frame and IR light captured for a frame.)
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri with the teachings of Ricardo to improve the resulting synthesized image by using determine a reconstruction loss, perceptual loss on blended color images, and a completeness loss (Ricardo- ¶0100).
Regarding claim 8, Gowri and Ricardo teach and/or suggest all the limitations of claim 7.
However, Gowri does not teach explicitly:
further comprising a masking module configured to:before the first pair of images is input to the model, mask pixels of the at least the first portion of the first human in a first one of the images of the first pair of images; and before the second pair of images is input to the model, mask pixels of the at least the second portion of the second human in a second one of the images of the second pair of images.
In the same field of endeavor, Ricardo teaches:
further comprising a masking module configured to:before the first pair of images is input to the model, mask pixels of the at least the first portion of the first human in a first one of the images of the first pair of images; and before the second pair of images is input to the model, mask pixels of the at least the second portion of the second human in a second one of the images of the second pair of images (i.e. see fig. 4).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri with the teachings of Ricardo to improve the resulting synthesized image by using determine a reconstruction loss, perceptual loss on blended color images, and a completeness loss (Ricardo- ¶0100).
Regarding claim 9, Gowri and Ricardo teach and/or suggest all the limitations of claim 8.
However, Gowri does not teach explicitly:
wherein the masking module is configured to mask a predetermined percentage of the pixels of the first and second ones of the images.
In the same field of endeavor, Ricardo teaches:
wherein the masking module is configured to mask a predetermined percentage of the pixels of the first and second ones of the images (i.e. see fig. 4).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri with the teachings of Ricardo to improve the resulting synthesized image by using determine a reconstruction loss, perceptual loss on blended color images, and a completeness loss (Ricardo- ¶0100).
Regarding claim 11, Gowri and Ricardo teach and/or suggest all the limitations of claim 8.
However, Gowri does not teach explicitly:
wherein the masking making module is configured to not mask background pixels.
In the same field of endeavor, Ricardo teaches:
wherein the masking making module is configured to not mask background pixels (i.e. see fig. 4).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri with the teachings of Ricardo to improve the resulting synthesized image by using determine a reconstruction loss, perceptual loss on blended color images, and a completeness loss (Ricardo- ¶0100).
Regarding claim 13, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein the first portion of the first human includes only at least a portion of one or more hands of the first human, and wherein the second portion of the second human includes only at least a portion of one or more hands of the second human (i.e. see fig. 3A).
Regarding claim 14, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein the first portion of the first human includes a body of the first human, and wherein the second portion of the second human includes a body of the second human (fig. 3B).
Regarding claim 15, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
the training module is further configured to:
construct a third pair of images of at least a third portion of a third human captured at different times;
construct a fourth pair of images of at least a fourth portion of a fourth human captured at the same time from different points of view;
input the third pair of images to the model; and
input the fourth pair of images to the model, the model is further configured to:
generate a third reconstructed image of the at least the third portion of the third human based on the third pair of images;
generate a fourth reconstructed image of the at least the fourth portion of the fourth human based on the fourth pair of images; and
the training module is configured to selectively adjust the one or more parameters of the model further based on:
a third difference between the at least the third portion of the third human in the third reconstructed image with a third predetermined image including the at least the third portion of the third human; and
a fourth difference between the at least the fourth portion of the fourth human in the fourth reconstructed image with a fourth predetermined image including the at least the fourth portion of the fourth human(i.e. comprising training the neural network, wherein training includes end-to-end training facilitating access to additional training data if the neural network serving as a main network is segmented into sub-components, wherein the neural network comprises a convolutional neutral network (CNN)- claim 13).
Regarding claim 16, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein an ethnicity of the first human is different than an ethnicity of the second human (Examiner’s Notes: Non-Functional Descriptive material- MPEP 2111.05).
Regarding claim 17, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein an age of the first human is at least 10 years older or younger than an age of the second human (Examiner’s Notes: Non-Functional Descriptive material- MPEP 2111.05).
Regarding claim 18, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein a gender of the first human is different than a gender of the second human (Examiner’s Notes: Non-Functional Descriptive material- MPEP 2111.05, see fig. 3B).
Regarding claim 19, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein a pose of the first human is different than a pose of the second human (Examiner’s Notes: Non-Functional Descriptive material- MPEP 2111.05, see fig. 3B).
Regarding claim 20, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein a background behind the first human is different than a background behind the second human (Examiner’s Notes: Non-Functional Descriptive material- MPEP 2111.05, see fig. 3B).
Regarding claim 22, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein a first texture of clothing on the first human is different than a second texture of clothing on the second human (Examiner’s Notes: Non-Functional Descriptive material- MPEP 2111.05, fig. 3B).
Regarding claim 23, Gowri and Ricardo teach and/or suggest all the limitations of claim 7 and Gowri further teaches:
wherein a first body shape of the first human is one of larger than and smaller than a second body shape of the second human (Examiner’s Notes: Non-Functional Descriptive material- MPEP 2111.05, see fig. 3B)..
Regarding claim 24, Gowri and Ricardo teach and/or suggest all the limitations of claim 7.
However, Gowri does not teach explicitly:
wherein the training module is configured to selectively adjust the one or more parameters of the model based on minimizing a loss determined based on the first difference and the second difference.
In the same field of endeavor, Ricardo teaches:
wherein the training module is configured to selectively adjust the one or more parameters of the model based on minimizing a loss determined based on the first difference and the second difference (i.e. the neural network is trained based on minimizing an occlusion loss function between the synthesized image generated by the neural network and a ground truth image captured by at least one witness camera- ¶0011).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri with the teachings of Ricardo to improve the resulting synthesized image by using determine a reconstruction loss, perceptual loss on blended color images, and a completeness loss (Ricardo- ¶0100).
Regarding claim 28, method claim 28 corresponds to apparatus claim 7, and therefore is also rejected for the same reasons of obviousness as listed above.
Regarding claim 29, method claim 29 corresponds to apparatus claim 8, and therefore is also rejected for the same reasons of obviousness as listed above.
Regarding claim 30, method claim 30 corresponds to apparatus claim 9, and therefore is also rejected for the same reasons of obviousness as listed above.
Regarding claim 32, method claim 32 corresponds to apparatus claim 11, and therefore is also rejected for the same reasons of obviousness as listed above.
Regarding claim 34, method claim 34 corresponds to apparatus claim 13, and therefore is also rejected for the same reasons of obviousness as listed above.
Claims 10, 26 and 31 are rejected under 35 U.S.C. 103 as being unpatentable over Gowri Somanath et al. [US 20190066733 A1] in view of Ricardo Martin Brualla et al. [US 20220398705 A1] and further in view of Christoph Feichtenhofer et al. [Masked Autoencoders As Spatiotemporal Learners].
Regarding claim 10, Gowri and Ricardo teach and/or suggest all the limitations of claim 9.
However, Gowri and Ricardo do not teach explicitly:
wherein the predetermined percentage is approximately 75 percent of the pixels of the first and second humans in the first and second ones of the images.
In the same field of endeavor, Christoph teaches:
wherein the predetermined percentage is approximately 75 percent of the pixels of the first and second humans in the first and second ones of the images (i.e. see fig 4(c)).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri and Ricardo with the teachings of Christoph to greatly improves generalization performance (Christoph- page. 2, ¶2).
Regarding claim 26, Gowri and Ricardo teach and/or suggest all the limitations of claim 7.
However, Gowri and Ricardo do not teach explicitly:
wherein the training module is further configured to, after the selectively adjusting one or more parameters of the model, fine tune training the model for a predetermined task.
In the same field of endeavor, Christoph teaches:
wherein the training module is further configured to, after the selectively adjusting one or more parameters of the model, fine tune training the model (i.e. training from scratch, while it takes less wall-clock training time overall
(pre-training plus fine-tuning)- page 2, ¶2… We do MAE self-supervised pre-training and then fine-tune the encoder with supervision for evaluation- page 5, ¶9) for a predetermined task (i.e. This shows that MAE is a practical solution to video recognition- page 6, ¶2).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri and Ricardo with the teachings of Christoph to greatly improves generalization performance (Christoph- page. 2, ¶2).
Regarding claim 31, method claim 31 corresponds to apparatus claim 10, and therefore is also rejected for the same reasons of obviousness as listed above.
Claims 12 and 33 are rejected under 35 U.S.C. 103 as being unpatentable over Gowri Somanath et al. [US 20190066733 A1] in view of Ricardo Martin Brualla et al. [US 20220398705 A1] and further in view of Mark Jeffrey Matthews et al. [US 20240371081 A1].
Regarding claim 12, Gowri and Ricardo teach and/or suggest all the limitations of claim 8.
However, Gowri and Ricardo do not teach explicitly:
wherein the training module is further configured to identify boundaries of the first and second humans.
In the same field of endeavor, Mark teaches:
wherein the training module is further configured to identify boundaries of the first and second humans (i.e. FIG. 7 further depicts a segmentation mask 904 & 908 for each input image- ¶0132).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri and Ricardo with the teachings of Mark to improve the generalization capability of the models being trained (Mark- ¶0090).
Regarding claim 33, method claim 33 corresponds to apparatus claim 12, and therefore is also rejected for the same reasons of obviousness as listed above.
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Gowri Somanath et al. [US 20190066733 A1] in view of Ricardo Martin Brualla et al. [US 20220398705 A1] and further in view of Adam Rowell et al. [US 20200342652 A1].
Regarding claim 21, Gowri and Ricardo teach and/or suggest all the limitations of claim 8.
However, Gowri and Ricardo do not teach explicitly:
wherein the training module is configured to determine the loss value based on a sum of the first difference and the second difference.
In the same field of endeavor, Adam teaches:
wherein the training module is configured to determine the loss value based on a sum of the first difference and the second difference (i.e. the disparity of a pixel is equal to the shift value that leads to a minimum sum of squared differences for that pixel (i.e., the lowest difference between the sum of squared differences and the sum of absolute differences)- ¶0073).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention, to modify the teachings of Gowri and Ricardo with the teachings of Adam to improve efficiency and reduce latency during transmission and/or pre-processing of synthetic image datasets (Adam----- ¶0135).
Claim 25 is rejected under 35 U.S.C. 103 as being unpatentable over Gowri Somanath et al. [US 20190066733 A1] in view of Ricardo Martin Brualla et al. [US 20220398705 A1] and further in view of Yuichi Kageyama et al. [US 20090202222 A1].
Regarding claim 25, Gowri and Ricardo teach and/or suggest all the limitations of claim 24.
However, Gowri and Ricardo do not teach explicitly:
wherein the different times are at least 2 seconds apart.
In the same field of endeavor, Yuichi teaches:
wherein the different times are at least 2 seconds apart (i.e. Many information processing devices such as personal computers and the like are equipped with slide show functions that take still images that have been captured by a digital camera or the like and automatically display them in a sequence, each for a specified time period, such as five seconds, for example-¶0005).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Gowri and Ricardo with the teachings of Yuichi to reduce the effect on the display timing of the time it takes for the playback device 200 to acquire the image B, such that the images can be displayed continuously at fixed intervals (Yuichi- ¶0112).
Claim 27 is rejected under 35 U.S.C. 103 as being unpatentable over Gowri Somanath et al. [US 20190066733 A1] in view of Ricardo Martin Brualla et al. [US 20220398705 A1] and further in view of Christoph Feichtenhofer et al. [Masked Autoencoders As Spatiotemporal Learners] and even further in view of Nikos Kolotouros et al. [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop].
Regarding claim 27, Gowri, Ricardo and Christoph teach and/or suggest all the limitations of claim 26.
However, Gowri, Ricardo and Christoph do not teach explicitly:
wherein the predetermined task is one of:
determining a mesh of an outer surface of a hand of a human captured in an input image;
determining a mesh of an outer surface of a body (head, torso, arms, legs, etc.) of a human captured in an input image;
determining coordinates of an outer surface of a body of a human captured in an input image;
determining a three dimensional pose of a human captured in an input image; and determining a mesh of an outer surface of a body of a human captured in a pair of images.
In the same field of endeavor, Nikos teaches:
wherein the predetermined task is one of:
determining a mesh of an outer surface of a hand of a human captured in an input image;
determining a mesh of an outer surface of a body (head, torso, arms, legs, etc.) of a human captured in an input image (i.e. Figure 2: Overview of the proposed approach. SPIN trains a deep network for 3D human pose and shape estimation through a tight collaboration between a regression-based and an iterative optimization-based approach. During training, the network predicts the parameters reg of the SMPL parametric model [20]. Instead of using the ground truth 2D keypoints to apply a weak reprojection loss, we instead propose to use our regressed estimate to initialize an iterative optimization routine that fits the model to 2D keypoints (SMPLify). This procedure is done within the training loop. The optimized model parameters opt are used to explicitly supervise the output of the network and supply it with privileged model-based supervision, that is beneficial compared to the weaker and typically ambiguous 2D reprojection losses. This collaboration leads to a self-improving loop, since better fits help the network train better, while better initial estimates from the network help the optimization routine converge to better fits- page 2);
determining coordinates of an outer surface of a body of a human captured in an input image;
determining a three dimensional pose of a human captured in an input image; and determining a mesh of an outer surface of a body of a human captured in a pair of images.
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Gowri, Ricardo and Christoph with the teachings of Nikos since better network estimates can lead the optimization to better solutions, while more accurate optimization fits provide better supervision for the network (Nikos- Abstract).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CLIFFORD HILAIRE whose telephone number is (571)272-8397. The examiner can normally be reached 5:30-1400.
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, SATH V PERUNGAVOOR can be reached at (571)272-7455. 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.
CLIFFORD HILAIRE
Primary Examiner
Art Unit 2488
/CLIFFORD HILAIRE/Primary Examiner, Art Unit 2488
Prosecution Insights