DETAILED ACTION
Election/Restrictions
Applicant’s election without traverse of invention I in the reply filed on 8/25/2026 is acknowledged.
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 1-6,8-14,16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kurbiel( US 20230048926) in view of Han ( "Volume Feature Rendering for Fast Neural Radiance Field Reconstruction", May 2023).
Regarding claim 1, Kurbiel teaches a computer-implemented method for synthesizing an image, comprising:
capturing data from a scene([0007], camera data);
fusing grid-based representations of the scene([0142], the grid map representation of static environment data may be encoded using a static context encoder) from a plurality of different encodings to inherit beneficial properties of the plurality of different encodings, the plurality of different encodings including a Lidar encoding and a high definition map encoding ( [0165-0169], The static context 1304 may be represented by one or more of the following: Rasterized image from the HD (high definition) map …the detected drivable area from sensors, such as camera, lidar or radar) ;
Kurbiel does not expressly teach
rendering rays from fused grid-based representations;
determining a density for points in the rays;
determining a color for the points in the rays;
volume rendering the rays with the density and color; and synthesizing an image from volume rendered rays with the density and the color.
However, Han teaches
rendering rays from grid-based representations( page 5, The occupancy grid is used for efficient sampling on the NeRF synthetic dataset);
determining a density for points in the rays( page 5, The density of a sample xi is derived from the queried feature vector F(xi) );
determining a color for the points in the rays( Page 4, subsequent NN is then applied to transform the feature vector to the final rendered color; Page 5, a directional MLP to predict the final rendered color) ;
volume rendering the rays with the density and color( Page 5, We implement the proposed VFR using the NerfAcc library ) ; and
synthesizing an image from volume rendered rays with the density and the color ( Figure 4).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teaching of Kurbiel and Han, by using the dataset in Kurbiel as dataset for volume feature rendering as taught by Han, with motivation of “a better rendering quality while maintaining a similar training time” ( Han, page 4).
Regarding claim 2, Kurbiel in view of Han teaches the method of claim 1, further comprising mapping three-dimensional points in features vectors with a hash grid( Han, Page 5, The learnable features are organized by a multiresolution hash grid (MHG) … In the MHG, the number of feature channels in each layer is two and the positions of voxels will be hashed to a one-dimensional table if the number of voxels is larger than 219 ) .
Regarding claim 3, Kurbiel in view of Han teaches the method of claim 2, wherein fusing grid-based representations includes concatenating the hash grid, a grid of the Lidar encoding and a grid of the high definition map encoding (Kurbiel, ( [0165-0169], The static context 1304 may be represented by one or more of the following: Rasterized image from the HD (high definition) map …the detected drivable area from sensors, such as camera, lidar or radar) .
Regarding claim 4, Kurbiel in view of Han teaches the method of claim 3, further comprising extrapolating novel views ( Han, Figure 4) from concatenated information from the hash grid( Han, Page 5, a comprehensive encoding vector, which will be concatenated with a view-independent bottleneck feature vector) , the grid of the Lidar encoding and the grid of the high definition map encoding(Kurbiel, ( [0165-0169], The static context 1304 may be represented by one or more of the following: Rasterized image from the HD (high definition) map …the detected drivable area from sensors, such as camera, lidar or radar).
Regarding claim 5, Kurbiel in view of Han teaches the method of claim 1, wherein determining the density for points in the rays includes decoding density using a multi-layer perceptron( Han, page 5, The NN contains a spatial MLP and a directional MLP. The spatial MLP has two layers and the directional MLP has four layers … The density of a sample xi is derived from the queried feature vector F(xi) by a tiny density mapping layer).
Regarding claim 6, Kurbiel in view of Han teaches the method of claim 1, wherein determining the color for points in the rays includes decoding color using a multi-layer perceptron( Han, Figure 3; Page 4, subsequent NN is then applied to transform the feature vector to the final rendered color; Page 5, a directional MLP to predict the final rendered color).
Regarding claim 8, Kurbiel in view of Han teaches the method of claim 1, further comprising training a self-driving vehicle using synthesized images from the volume rendered rays ( Kurbiel,[0021]-[0026], the static context may represent objects which do not move (for example roads, buildings, or trees)… [0023], The dynamic context may include the whole road users' state, which may also include the ego vehicle; [0166] Rasterized image from the HD (high definition) map, wherein the high-definition map may cover the accurate lane markings position, so a vehicle's position may be accurately localized in the lanes).
Claims 9-14,16 recite the system for the method in claims 1-6,8. Since Kurbiel also teaches a system ( [0237] –[0239]), claims 9-14,16 are a rejected.
Claim(s) 7 and 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kurbiel in view of Han, further in view of Zhao(US 20230360372).
Regarding claim 7, Kurbiel in view of Han teaches the method of claim 1.
Kurbiel in view of Han does not expressly teach further comprising generating depth maps; and filtering data of the depth maps using a depth threshold and depth offset to prioritize nearer depth samples during training.
However, Zhao teaches generating depth maps([0004], the depth maps of the objects depicted in the set of content items can be determined by calculating internal and external parameters of cameras from which the set of content items was captured. Coarse point clouds associated with the objects depicted in the set of content items can be determined based on the internal and external parameters); and filtering data of the depth maps using a depth threshold and depth offset to prioritize nearer depth samples during training ([0008], the pixels in each content item of the set of content items to be filtered out can be determined by determining pixels in each content item of the set of content items that are outside a threshold depth range indicated by a corresponding depth map of each content item. The threshold depth range can indicate a depth range of an object depicted in each content item).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to combine the teaching of Kurbiel in view of Han with that of Zhao, by filtering the dataset in Kurbiel in view of Han based on a depth map based on the objects in the dataset as taught by Zhao, with motivation “to obtain a set of content items to train a neural radiance field-based (NeRF-based) machine learning model for object recognition” ( Zhao, Abstract).
Claim 15 recite the system for the method in claim 7. Since Kurbiel also teaches a system ( [0237] –[0239]), claim 15 is rejected.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JIANGENG SUN whose telephone number is (571)272-3712. The examiner can normally be reached 8am to 5pm, EST, M-F.
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, Randolph Vincent can be reached at 571 272 8243. 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.
JIANGENG SUN
Examiner
Art Unit 2661
/Jiangeng Sun/Examiner, Art Unit 2671
Prosecution Insights