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 .
Response to Amendment
The Amendment filed March 3rd 2026 has been entered. Claims 1-30 are pending in the application.
Response to Arguments
Applicant's arguments filed March 3rd 2026 have been fully considered but they are not persuasive.
In contrast to Liu 2021, Yao, and Visionmongers, Liu 2024 was previously cited with respect to the amended limitation, and therefore this response is directed towards the arguments raised with respect to Liu 2024.
Specifically, in responding to the after-final argument filed February 3rd 2026 (which appear to be identical to the arguments filed for continued examination), the Examiner argued that “The Examiner submits that one of ordinary skill in the art would understand "concatenating" (i.e., linking (things) together in a chain or series) to be analogous to "fusing" when assembling the feature map. Therefore, when each pixel feature can be considered to be part of a feature map, concatenating the features of each pixel to generate a feature map is analogous to fusing the feature maps.”
However, the Applicant’s remarks highlighted that “the feature maps in Liu 2024 are related to pixels of a single image rather than feature maps for multiple images”, and amended accordingly. The Examiner acknowledges that Figure 13 of Liu 2024 does not depict feature maps from multiple images, however, Liu 2024 discloses fusing features obtained from multiple views: “the flattened features at each view may be fused by a chosen aggregation function σ to produce the input feature to the decoder” [0135]. Each view may be a different image, as showcased in Figure 11 of Liu 2024, which showcases “an example of captured multi-view images” [0037]. See the updated mapping of claim 1 for more details.
For the above reason, the Examiner is not convinced that “Liu 2024 (individually or when combined with Liu 2021 and Yao) also fails to teach or reasonably suggest at least "fusing the plurality of feature maps based on features of the plurality of feature maps along a common axis to generate an aligned feature map, wherein each feature map of the plurality of feature maps corresponds to a different image of the plurality of images," as recited in claim 1.”
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.
Claims 1, 11, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Liu (US 20210390789 A1; hereinafter Liu 2021) in view of Liu (US 20240119671 A1; hereinafter Liu 2024).
Regarding claim 1:
Liu 2021 teaches:
A method for generating a representation of a face (Liu 2021: The method can generate, based on the UV face position map, a 3D model of the face, Abstract), the method comprising:
obtaining a plurality of images of a face (Liu 2021: In some implementations, the image processing system 100 can perform face image augmentation and generate facial images with rotated faces from multiple images captured by the image sensor device [0046]);
extracting features for each image of the plurality of images (Liu 2021: For example, the compute components 110 can […] extract features and information (e.g., color information, texture information, semantic information, etc.) from the image data, etc. [0055])
Liu 2021 fails to teach:
extracting features for each image of the plurality of images to generate a plurality of feature maps; and
fusing the plurality of feature maps based on features of the plurality of feature maps along a common axis to generate an aligned feature map, wherein each feature map of the plurality of feature maps corresponds to a different image of the plurality of images.
Liu 2024 teaches:
A method for generating a representation of a face (Liu 2024: methods for reconstructing complete face models [0003]), the method comprising:
obtaining a plurality of images of a face (Liu 2024: receiving one or more input images in an image space of a face, [0021]);
extracting features for each image of the plurality of images to generate a plurality of feature maps (Liu 2024: iteratively computing or producing a feature map via visual semantic correlation between the UV space and the image space and regress geometry updates, [0021]; see Note 1A); and
fusing the plurality of feature maps based on features of the plurality of feature maps (Liu 2024: the flattened features at each view may be fused by a chosen aggregation function σ to produce the input feature to the decoder [0135]; see Note 1B) along a common axis to generate an aligned feature map (Liu 2024: In order to solve the alignment problem, the features in the UV space and the image space are joined in a unified feature space, such that the corresponding locations in both spaces are trained to encode similar features, [0129]; see Note 1C), wherein each feature map of the plurality of feature maps corresponds to a different image of the plurality of images (see Note 1D).
Note 1A: Liu 2024 teaches: “receiving one or more input images” [0021]. Liu further teaches: “extracting geometry feature and texture feature in the image space; extracting features in a UV space”. Liu 2024 showcases in Figure 5 that the geometry feature and texture feature are extracted from “Input image I”. Therefore, it is reasonable to conclude that Liu 2024 extracts features from the one or more input images.
Liu 2024 also teaches: “FIG. 5 illustrates a visual-semantic correlation (VSC) for preparing a 2D feature map.” One of the inputs for the 2D feature map is the input image I shown on the left of the figure. Therefore, it is reasonable to conclude that when Liu 2024 extracts features from the one or more input images, one or more 2D feature maps will be received.
Note 1B: Liu 2024 teaches: “in embodiments, FIG. 5 shows that a multi-scale 3D local grid may be built around the 3D position of each pixel in the UV space and the grid points projected to the image space. Then the 6D correlation may be computed and flattened to a 2D feature map.” [0096]. Therefore, as best understood by the Examiner, the flattened features are 2D feature maps. As cited above in [0135], Liu 2024 further teaches that the feature maps “at each view” may be fused to produce an “input feature”.
Note 1C: The Examiner understands that the generated feature map is aligned, because Liu 2024 teaches: “the disclosed formulation offers a direct benefit to the texture inference module, as the pixel-aligned signals between the UV space and the multi-view inputs arc already prepared in the previous geometry inference step.” [0137]. Liu teaches that alignment will align the features in each image by UV: “In order to solve the alignment problem, the features in the UV space and the image space are joined in a unified feature space, such that the corresponding locations in both spaces are trained to encode similar features.” [0129].
The specification of the present application teaches: “images at multiple resolutions that have been aligned to a common axis, such as a UV axis of UV space” [0025]. Therefore, because Liu 2024 teaches alignment based on the UV-space, the Examiner understands Liu 2024 to teach alignment to a common axis.
Note 1D: Liu 2024 elaborates about the aggregation function σ that it aggregates UV space features across all views: “in embodiments, the UV-space features may be aggregate with the aggregation function: where σ is the aggregation function that aggregates the pixel-wise feature across all views, which could be max, min, var, etc.” [0137]. As well as in [0135] cited above, Liu 2024 teaches that multiple views may be fused or aggregated. Said views may be different images, as showcased in Fig. 11 of Liu 2024, which showcases “an example of captured multi-view images” [0037]. Accordingly, the Examiner understands Liu 2024 to teach “wherein each feature map of the plurality of feature maps corresponds to a different image of the plurality of images”.
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Liu 2024 with Liu 2021. Extracting features for each image of the plurality of images to generate a plurality of feature maps; and fusing the plurality of feature maps based on features of the plurality of feature maps along a common axis to generate an aligned feature map, as in Liu 2024, would benefit the Liu 2021 teachings by ensuring that each detected feature of the image can be managed separately by the system and that the features are aligned properly when an image must be composited. (Liu: The initialized face geometry, when projected to the image space, will show misalignment with the underlying geometry depicted in the multi-view images, [0129])
Regarding claim 11:
Claim 11 is substantially similar to claim 1, and is therefore rejected for similar reasons. Claim 11 contains the following notable differences:
Claim 11 claims an apparatus instead of a method. Liu 2021 teaches an apparatus: “an apparatus is provided for face image augmentation is provided” [0005].
Regarding claim 21:
Claim 21 is substantially similar to claim 1, and is therefore rejected for similar reasons. Claim 21 contains the following notable differences:
• Claim 21 claims a non-transitory computer-readable storage medium instead of a method. Liu 2021 teaches a non-transitory computer-readable medium: “a non-transitory computer-readable medium is provided for face image augmentation is provided. In some aspects, the non-transitory computer-readable medium can include instructions that, when executed by one or more processors, cause the one or more processors to …” [0006].
Claims 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 18, 19, 20, 22, 23, 24, 25, 26, 27, 28, 29, and 30 are rejected under 35 U.S.C. 103 as being unpatentable over Liu 2021 (US 20210390789 A1) in view of Liu 2024 (US 20240119671 A1), and The Foundry Visionmongers Ltd (NPL: UV Mapping).
Regarding claim 2:
Liu 2021 in view of Liu 2024 teaches:
The method of claim 1 (as shown above), further comprising:
obtaining a generic 3D morphable model (3DMM) of a face, the generic 3DMM including a plurality of vertices (Liu 2021: FIG. 5 illustrates an example 3D morphable head model, [0027]; see Note 2A);
projecting the generic 3DMM to two dimensions (Liu 2021: The 3DMM head shape can be projected onto an image plane with weak perspective projection, [0105]; see Note 2B) based on the common axis (see Note 2C) to generate a mean face position map (see Note 2C);
Note 2A: Liu 2021 teaches a 3DMM in Fig. 5, which comprises a face. Furthermore, the topology of the 3DMM is visible, wherein the vertices are marked by the intersections of the lines on the drawing. Therefore, the 3DMM includes a plurality of vertices.
Note 2B: A plane is two dimensional, so the 3DMM is projected to two dimensions.
Note 2C: As shown in Note 2B, the 3DMM is projected to a two dimensional plane. The specification of the present application recites: “The mean face position map may be 2D projection of a generic (e.g., mean, default) 3D mesh model of the object,” [0026]. Therefore, the 2D projection taught by Liu 2021 is analogous to the mean face position map.
Furthermore, when the 3DMM head shape is projected to an image plane, the projection is analogous to creating a UV map. A UV Map in the art is known to be a mapping or projection of 3D vertices to a 2D texture (The Foundry Visionmongers Ltd: A UV Map is a type of vertex map that stores vertical and horizontal positions on a 2D texture. The letters U (Horizontal) and V (Vertical) denote the axes of the 2D texture, Pg. 1, par. 1). For example, compare Figure 7.5 of The Foundry Visionmongers Ltd to Figure 13 of Liu 2024. In Note 1B above, it was shown that the feature map is aligned to UV space. Therefore, it would be obvious to one of ordinary skill in the art to ensure the alignment of the projection of the 3DMM head shape is the same as the feature map alignment discussed in Note 1B above.
Liu 2021 fails to teach:
determining one or more correspondences between features of the aligned feature map and vertices of the mean face position map to generate a first residual position map; and
combining the first residual position map with the mean face position map to generate an intermediate position map.
Liu 2024 teaches:
determining one or more correspondences between features of the aligned feature map and vertices of the mean face position map (Liu 2024: DIFF further updates the UV position map and the camera pose iteratively using an RNN-based neural optimizer from the feature correlation between the UV space and the image space [0080]; see Note 2D) to generate a first residual position map (Liu 2024: the residual of the position map δM [0101]; see Note 2D); and
combining the first residual position map (Liu 2024: To predict the update tuple, according to embodiments, a 2D feature map is constructed containing the signals where δM(t) and [δR(t), δt(t)] should orient, [0134]; see Note 2E) with the mean face position map (Liu 2024: Specifically, let M̂(t) = R(t) M(t) + t(t) be the transformed position map at t-th step, [0135]; see Note 2F) to generate an intermediate position map (see Note 2F).
Note 2D: Liu 2024 teaches that “deep iterative face fitting (DIFF), a non-parametric approach based on feature correlation” [0080] will be used to update the UV position map (as in [0080] cited above) based on a feature correlation between the UV space and image space. Liu 2024 further teaches: “FIG. 4 illustrates an overview of an exemplary pipeline for a given input image when processed by the disclosed DIFF method and system,” [0085]. In Fig. 4, Liu 2024 showcases that VSC receives input from the “UV-space feature map G” and “M(0)”, where M is the mean face position map (as shown in Note 2F below). Because DIFF generates correlation data between the mean face position map and the UV-space feature map, Liu 2024 teaches determining one or more correspondences between features of the aligned feature map and vertices of the mean face position map.
Liu 2024 teaches: “the resulting feature vector y(t) may be used as the output of the visual semantic correlation network. Liu 2024 further teaches: “Given the hidden state h(t), the geometry decoding network outputs […] the position correction map δM(t),” [0101]. The hidden state is calculated by the following equation (Liu 2024, [0131]):
PNG
media_image1.png
24
378
media_image1.png
Greyscale
That is, the hidden state at step t is based on the feature vector from the correlation, and the previous hidden state at step t-1.
Because Liu teaches that the position correction map is analogous to a residual of the position map: “the residual of the position map δM,” [0101], and the position correction map is generated based on the hidden state obtained from the feature vector representing the correlation data, Liu teaches determining one or more correspondences between features of the aligned feature map and vertices of the mean face position map to generate a first residual position map.
Note 2E: Liu 2024 teaches: “the position map M may be updated as well as the head pose [R, t] separately, given the correlation tensor between the two misaligned feature maps of interest, namely the UV feature map g and the image space feature f,” [0131]. As cited above, Liu further teaches: “according to embodiments, a 2D feature map is constructed containing the signals where δM(t) and [δR(t), δt(t)] should orient,” [0134]. Note that δM(t) is the residual feature map cited in (Liu 2024, [0101]) above. Because the residual position map is used to calculate a feature map that is then used to update the position map (further details on the updating in Note 2F), Liu 2024 teaches that the first residual position map may be combined with the mean face position map to generate an updated position map.
Note 2F: Liu 2024 teaches that the position map M is updated according to this equation: “In the following paragraphs, there is described in detail how the disclosed optimizer initializes, updates, and finalizes the corrections in order to recover M…” [0133]. Liu 2024 teaches: “A UV-space position map that represents the geometry may be first initialized to be the mean face shape, according to embodiments,” [0129]. That is, prior to updating, the position map M is initialized to be a mean face position map. As cited above, the position map is updated to “M̂(t)”, which is analogous to the intermediate position map.
Before the effective filing date of the claimed invention, it would have been obvious to a person having ordinary skill in the art to combine the teachings of Liu 2024 with Liu 2021. Determining one or more correspondences between features of the aligned feature map and vertices of the mean face position map to generate a first residual position map; and combining the first residual position map with the mean face position map to generate an intermediate position map., as in Liu 2024, would benefit the Liu 2021 teachings by ensuring that features are matched as accurately as possible while avoiding overfitting to specific features or geometry. (Liu 2024: Such results may be achieved with less than 200 training subjects, which demonstrates the generalizability of the disclosed model across identity, thanks to iterative correlation design that learns the local semantic features, [0113])
Regarding claim 3:
Liu 2021 in view of Liu 2024, and The Foundry Visionmongers Ltd teaches:
The method of claim 2 (as shown above), wherein
determining the one or more correspondences comprises determining one or more displacement values (Liu 2024: The first is the use of a UV-space position map for representing geometry, where each pixel is mapped to the position of a surface vertex. Such representation […] organically aligns the geometry and texture space for the inference of high-frequency displacement maps ... [0062]; Liu 2024: The recurrent optimization is centered around a per-pixel visual semantic correlation (VSC) that serves to iteratively refine the face geometry, [0062]; see Note 3A) between features of the aligned feature map and vertices of the mean face position map (see Note 3B), and
wherein the first residual position map includes the one or more displacement values (see Note 3A).
Note 3A: In Fig. 4 of Liu 2024, it is shown that VSC accepts the position map M as input. Given that the position map comprises vertex positions, updating the position map inherently requires displacing the vertices of the position map.
Furthermore, as shown above in Note 2F, the position map M is updated to “M̂(t)”. Therefore, any displacement of the vertices will be encoded in M̂(t). Because Liu 2024 “iteratively comput[es] […] a feature map via visual semantic correlation between the UV space and the image space and regress geometry updates,” [0021], it is reasonable to conclude that the displacement encoded in the position map at step t will remain when the system completes further iterations.
Note 3B: As shown in Note 2D, the one or more correspondences are determined based on features of the aligned feature map and vertices of the mean face position map.
Regarding claim 4:
Liu 2021 in view of Liu 2024, and The Foundry Visionmongers Ltd teaches:
The method of claim 2 (as shown above), wherein the one or more correspondences are also determined based on a label map labeling portions of the mean face position map (see Note 4A).
Note 4A: Fig. 23 of Liu 2024 showcases that landmarks may be assigned to the position map. Specifically, Liu 2024 teaches that “Given valid UV mappings, the position map representation is amenable to conversions to various representations, as shown in each column. Specifically, the disclosed position map may be converted to different mesh topologies seamlessly as long as a solid UV mapping is provided,” [0170]. The sixth column from the left showcases landmarks, which is analogous to a label map that labels portions of the mean face position map.
It would be obvious to one of ordinary skill in the art to also determine correspondences based on the landmarks, because Liu teaches: “Landmarks and region maps representations can be extracted from the potential maps, which are suitable for many mobile applications,” [0170].
Regarding claim 5:
Liu 2021 in view of Liu 2024, and The Foundry Visionmongers Ltd teaches:
The method of claim 2 (as shown above), further comprising:
determining one or more correspondences between features of the aligned feature map and vertices of the mean face position map (Liu 2024: DIFF further updates the UV position map and the camera pose iteratively using an RNN-based neural optimizer from the feature correlation between the UV space and the image space [0080]; see Note 2D and Note 5A) to generate a second residual position map (Liu 2024: the residual of the position map δM [0101]; see Note 2D and Note 5A); and
combining the second residual position map (Liu 2024: To predict the update tuple, according to embodiments, a 2D feature map is constructed containing the signals where δM(t) and [δR(t), δt(t)] should orient, [0134]; see Note 2E and Note 5A) with the mean face position map (Liu 2024: Specifically, let M̂(t) = R(t) M(t) + t(t) be the transformed position map at t-th step, [0135]; see Note 2F and Note 5A) to generate a fine position map (see Note 2F and Note 5A).
Note 5A: As noted in Note 3A, Liu 2024 “iteratively comput[es] […] a feature map via visual semantic correlation between the UV space and the image space and regress geometry updates,” [0021]. That is, Liu may determine correlations or “correspondences” an indefinite amount of times (Liu 2024, Fig. 4, “Learned recurrent face geometry optimizers”), before outputting “refined geometry” [0062].
Regarding claim 6:
Liu 2021 in view of Liu 2024 and The Foundry Visionmongers Ltd teaches:
The method of claim 5 (as shown above), further comprising reprojecting the fine position map to three dimensions to obtain a fine face mesh (Liu 2021: In some cases, generating the 3D model of the face can include projecting the UV face position map to 3D space [0011]).
Regarding claim 7:
Liu 2021 in view of Liu 2024, and The Foundry Visionmongers Ltd teaches:
The method of claim 6 (as shown above), further comprising:
aligning textures of the plurality of images based on the fusing of the plurality of feature maps to generate a texture map (Liu 2024: The texture feature map is used for generating high-resolution texture maps [0127]; see Note 7A); and
applying the texture map to the fine face mesh to obtain a representation of the face (Liu 2024, Fig. 17; see Note 7B).
Note 7A: In Note 1B, it was shown that UV-space feature map G shares a common axis with three feature maps, and that fusing the plurality of feature maps is based on features of the plurality of feature maps along a common axis. Liu 2024 teaches: “a recurrent module then iteratively optimizes the geometry by projecting the image-space features to the UV space and comparing them with a reference UV-space feature. The optimized geometry may then provide pixel-aligned signals for the inference of high-resolution textures in such embodiments,” [0061]. The UV-space feature corresponds to the UV-space feature map G, and therefore, it would be obvious to one of ordinary skill in the art to generate “pixel-aligned signals” to generate high-resolution textures. Liu 2024 showcases examples of such textures in Fig. 4.
Note 7B: Liu 2024 teaches “FIG. 17 shows exemplary testing results as produced by the disclosed model implementing a known prior art setting,” [0146]. In the Figure, rendering is showcased with applied textures.
Regarding claim 8:
Liu 2021 in view of Liu 2024, and The Foundry Visionmongers Ltd teaches:
The method of claim 1 (as shown above), wherein the common axis comprise a U, V axis (see Note 8A).
Note 8A: Liu 2024 teaches: “the UV-space feature map G ∈ RWixHix36 may be assembled by concatenating the following features for each pixel u: (1) the 2D coordinates of u itself, normalized to [−1,1]2 (a); (2) the corresponding 3D coordinates of u in the mean face mesh (b); (3) the one-hot encoding of its face region,” [0128]. Because the three features listed above are sampled for each pixel u, it is reasonable to conclude that each feature is a feature map. Furthermore, Fig. 13 of Liu 2024 showcases that each of the three features a, b, and c may be interpreted as maps, or 2D images.
Fig. 13 of Liu 2024 showcases that each of the three features a, b, and c share a UV space, that is, all three maps may use the same UV map to properly map to a 3D mesh. This is visualized by the face mesh in the lower right of each feature map, as well as the fact that each map shares a similar layout. Therefore, it is reasonable to conclude that the features of the plurality of feature maps share a common axis, as otherwise the feature maps would not align properly.
When the feature maps are aligned within the UV space, it is inherent that they share a common axis relative to the U and V axis of the UV space.
Regarding claim 9:
Liu 2021 in view of Liu 2024, and The Foundry Visionmongers Ltd teaches:
The method of claim 1 (as shown above), plurality of images of a face comprises views of the face from a plurality of angles around the face (Liu 2024: In accordance with the present disclosure, a method for achieving realistic face modeling should at least: […] be robust to input images with extreme expressions and camera poses [0057]; see Note 9A).
Note 9A: Liu 2024 additionally showcases “Input multi-view images {Ii}” in the top left of Fig. 12 comprising views of the face from a plurality of angles around the face.
Regarding claim 10:
Liu 2021 in view of Liu 2024, and The Foundry Visionmongers Ltd teaches:
The method of claim 1 (as shown above), wherein features for each image of the plurality of images are extracted using a set a machine learning based feature extractors (Liu 2024: the pipeline may be divided into three parts: (1) a feature extraction network; [0085]; see Note 10A).
Note 10A: Liu showcases in Fig. 4 that the feature extraction networks comprise encoders, which are known in the art to be components of encoder-decoder neural networks. In this case, the decoders are part of the “Learned reccurent face geometry optimizers” and the “Texture inference networks”.
Regarding claim 12:
Claim 12 is substantially similar to claim 2, and is therefore rejected for similar reasons. Claim 12 contains the following notable differences:
Claim 12 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 13:
Claim 13 is substantially similar to claim 3, and is therefore rejected for similar reasons. Claim 13 contains the following notable differences:
Claim 13 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 14:
Claim 14 is substantially similar to claim 4, and is therefore rejected for similar reasons. Claim 14 contains the following notable differences:
Claim 14 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 15:
Claim 15 is substantially similar to claim 5, and is therefore rejected for similar reasons. Claim 15 contains the following notable differences:
Claim 15 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 16:
Claim 16 is substantially similar to claim 6, and is therefore rejected for similar reasons. Claim 16 contains the following notable differences:
Claim 16 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 17:
Claim 17 is substantially similar to claim 2, and is therefore rejected for similar reasons. Claim 17 contains the following notable differences:
Claim 17 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 18:
Claim 18 is substantially similar to claim 8, and is therefore rejected for similar reasons. Claim 18 contains the following notable differences:
Claim 18 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 19:
Claim 19 is substantially similar to claim 9, and is therefore rejected for similar reasons. Claim 19 contains the following notable differences:
Claim 19 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 20:
Claim 20 is substantially similar to claim 10, and is therefore rejected for similar reasons. Claim 20 contains the following notable differences:
Claim 20 claims an apparatus instead of a method. In the rejection of claim 11, it was shown that Liu 2021 teaches an apparatus.
Regarding claim 22:
Claim 22 is substantially similar to claim 2, and is therefore rejected for similar reasons. Claim 22 contains the following notable differences:
Claim 22 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 23:
Claim 23 is substantially similar to claim 3, and is therefore rejected for similar reasons. Claim 23 contains the following notable differences:
Claim 23 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 24:
Claim 24 is substantially similar to claim 4, and is therefore rejected for similar reasons. Claim 24 contains the following notable differences:
Claim 24 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 25:
Claim 25 is substantially similar to claim 5, and is therefore rejected for similar reasons. Claim 25 contains the following notable differences:
Claim 25 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 26:
Claim 26 is substantially similar to claim 6, and is therefore rejected for similar reasons. Claim 26 contains the following notable differences:
Claim 26 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 27:
Claim 27 is substantially similar to claim 2, and is therefore rejected for similar reasons. Claim 27 contains the following notable differences:
Claim 27 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 28:
Claim 28 is substantially similar to claim 8, and is therefore rejected for similar reasons. Claim 28 contains the following notable differences:
Claim 28 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 29:
Claim 29 is substantially similar to claim 9, and is therefore rejected for similar reasons. Claim 29 contains the following notable differences:
Claim 29 claims a non-transitory computer-readable storage medium instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches a non-transitory computer-readable medium.
Regarding claim 30:
Claim 30 is substantially similar to claim 10, and is therefore rejected for similar reasons. Claim 30 contains the following notable differences:
• Claim 30 claims an apparatus instead of a method. In the rejection of claim 21, it was shown that Liu 2021 teaches an apparatus.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Liu et al.: (NPL: Rapid Face Asset Acquisition with Recurrent Feature Alignment) corresponds to the patent reference Liu 2024 (US 20240119671 A1) relied upon above and may contain extra useful detail. It also contains higher resolution (although slightly altered) versions of the figures in Liu 2024.
Yang (US 11417053 B1) showcases a similar refinement method for the position map in Fig. 2.
Wu (NPL: MVF-Net: Multi-View 3D Face Morphable Model Regression) teaches reconstruction of a face from multiple views utilizing features obtained from each input image.
Yao (NPL: MVSNet: Depth Inference for Unstructured Multi-view Stereo) was previously cited to teach “extracting features for each image of the plurality of images to generate a plurality of feature maps that correspond to the plurality of images”.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VINCENT ALEXANDER PROVIDENCE whose telephone number is (571)270-5765. The examiner can normally be reached Monday-Thursday 8:30-5:00.
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.
/VINCENT ALEXANDER PROVIDENCE/Examiner, Art Unit 2617 /KING Y POON/Supervisory Patent Examiner, Art Unit 2617