DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Notice of Amendments
2. The Examiner acknowledges the amended claims filed on 07/17/2026.
- Claims 1 and 16 have been amended.
Response to Arguments
3. Applicant's arguments filed on 07/17/2026 with respect to claims 1-16 have been considered but are moot in view of the new ground(s) of rejection.
Claim Rejections - 35 USC § 103
4. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
5. 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.
6. Claims 1-2, 4-12 and 15-16 are rejected under 35 U.S.C. 103 as being unpatentable over Frosio et al. (US-PGPUB 2025/0069191) in view of Liu et al. (US-PGPUB 2019/0213439).
Regarding claim 1, Frosio discloses a method for multi-exposure high dynamic range (HDR) imaging (see figs. 1A-1C, 3A), the method comprising:
receiving an input sequence of images captured by at least one camera (Input image 101; see figs. 1A-2B. The input image is a frame of a video sequence and the process is repeated for additional input images included in the video sequence; see paragraphs 0017, 0049. Images provided by cameras; see paragraphs 0052, 0082, 0100), wherein the images of the input sequence are captured using one or more exposures (The training dataset includes images of many different scenes and, for each image, a set of M different exposure versions of the image is captured; see paragraph 0035);
applying a hallucination technique on one or more images of the input sequence, for generating a hallucinated set of images corresponding to a target exposure that lies within a target exposure range (Using large training datasets enables the image encoder 110, decoder 120, and image synthesis controller 115 to hallucinate and change the exposure levels in over- or under-exposed regions from a single input image. Controller 115 processes the latent representation to compute target (desired) enhancements that correspond to the exposure levels for synthesizing the set of exposure transformed images; see paragraphs 0033, 0027); and
generating an output sequence of HDR images at a same frame rate with which the input sequence is captured, by employing a first neural network (The method 300 shown in fig. 3A is implemented a processor PPU 400 implementing a neural network model; see paragraphs 0085, 0052, 0112. The process is repeated for additional input images included in the video sequence; see paragraphs 0017, 0049), each HDR image in the output sequence being generated using one of: a corresponding image from the hallucinated set, a corresponding image from the input sequence (One or more of the exposure transformed images are then merged to produce the output image 105; see fig. 1A and paragraph 0022. First, the synthesized transformations are apply to the input image to produce a set of exposure transformed images, then the output image is generated; see figs. 1A-1C, 3A and paragraphs 0049, 0028).
However, Frosio does not expressly disclose each HDR image in the output sequence being generated using at least a previously-generated HDR image of the output sequence.
On the other hand, Liu discloses each HDR image in the output sequence being generated using at least a previously-generated HDR image of the output sequence and one of: a corresponding image from the hallucinated set, a corresponding image from the input sequence (Given a few HDR key-frames and an LDR video, the TPN system 200 propagates task-specific data comprising scene radiance information from the key-frames to the remaining frames. The HDR information is propagated from a few HDR images input to the TPN system 200 to neighboring LDR frames. Therefore, the TPN system 200 provides an alternative solution for efficient, low cost HDR video reconstruction from a few provided HDR frames; see paragraphs 0070-0080 and figs. 2A-2B. The property data for the key-frame is high dynamic range data corresponding to the key-frame and the property data for the frame comprises high dynamic range data corresponding to the frame; see paragraph 0075).
Therefore, 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 teachings of Frosio and Liu to provide generating an output sequence of HDR images, by employing a first neural network, each HDR image in the output sequence being generated using at least a previously-generated HDR image of the output sequence and one of: a corresponding image from the hallucinated set, a corresponding image from the input sequence for the purpose of providing an efficient low cost HDR video reconstruction output.
Regarding claim 2, Frosio and Liu disclose everything claimed as applied above (see claim 1). In addition, Frosio discloses selecting the one or more images of the input sequence upon which the hallucination technique is to be applied, as those images which are captured using an exposure that is less than a predefined threshold, wherein the predefined threshold is less than or equal to the target exposure (Synthesis controller 115 to learn to hallucinate and change the exposure levels in under-exposed regions from a single input image; see paragraphs 0033, 0027).
Regarding claim 4, Frosio and Liu disclose everything claimed as applied above (see claim 2). In addition, Frosio discloses the input sequence of images comprises: a first set of images captured using a first exposure lying within a first exposure range, and a second set of images captured using a second exposure lying within a second exposure range, wherein the images of the first set are interleaved with the images of the second set, in the input sequence, wherein at least one of: the first exposure, the second exposure is less than the predefined threshold, and at least one of: the images of the first set, the images of the second set, are selected as the one or more images (A training dataset is obtained that includes “ground truth” images of a scene acquired using different exposures. During training, images in the dataset are selected as an input image and a set of the differently exposed images (e.g., different exposure time levels that are ⅛×, ¼×, ½×, 1×, and 2× an optimal exposure time) are used as a ground truth set of exposure transformed images; see paragraph 0033).
Regarding claim 5, Frosio and Liu disclose everything claimed as applied above (see claim 4). In addition, Frosio discloses controlling the at least one camera such that both the first exposure and the second exposure are less than the predefined threshold (The selected images can include differently exposed images, including exposure time levels that are ⅛×, ¼×, ½× of optimal exposure time; see paragraph 0033).
Regarding claim 6, Frosio and Liu disclose everything claimed as applied above (see claim 4). In addition, Frosio discloses controlling the at least one camera such that the first exposure is less than the predefined threshold while the second exposure is greater than or equal to the predefined threshold (The selected images can include differently exposed images, including exposure time levels that are ⅛× and 1× of optimal exposure time; see paragraph 0033).
Regarding claim 7, Frosio and Liu disclose everything claimed as applied above (see claim 6). In addition, Frosio discloses merging one or more images(One or more of the exposure transformed images are then merged to produce the output image 105; see fig. 1A and paragraph 0022)
Regarding claim 8, Frosio and Liu disclose everything claimed as applied above (see claim 6). In addition, Frosio discloses applying the hallucination technique on the first set of images for generating a third set of images corresponding to at least one intermediate exposure that lies between the first exposure and the second exposure, wherein at the step of generating the output sequence of HDR images, each HDR image in the output sequence is generated using also one or more images from the third set (For each of the different exposures, the image associated with the specific exposure is used as the ground truth output image. An exposure correction system that generates an exposure corrected output image and incorporates the exposure bracketing system 100 receives selected input images and specific exposures associated with the selected ground truth output images. Using large training datasets enables the image encoder 110, decoder 120, and image synthesis controller 115 to learn to reconstruct, hallucinate, and change the exposure levels in over- or under-exposed regions from a single input image; see paragraph 0033).
Regarding claim 9, Frosio and Liu disclose everything claimed as applied above (see claim 6). In addition, Frosio discloses the at least one camera comprises a first camera and a second camera that collectively form a stereo imaging pair, the first camera and the second camera being controlled to capture a first sequence of images and a second sequence of images respectively, at a same rate, such that the first camera and the second camera use different exposures from amongst the first exposure and the second exposure while capturing corresponding images of the first sequence and the second sequence (The system 565 includes stereoscopic camera systems; see paragraph 0100. During training, images in the dataset selected as an input image and a set of the differently exposed images are used as a ground truth set of exposure transformed images; see paragraph 0033).
Regarding claim 10, Frosio and Liu disclose everything claimed as applied above (see claim 9). In addition, Frosio discloses the step of applying the hallucination technique is performed in an alternating manner for a first set of images of the first sequence and a first set of images of the second sequence, using same processing resources (The input image is a frame in a video sequence, and steps 310, 320, 330, and combining the set of exposure transformed images is repeated for additional input images included in the video sequence to produce additional output images with corrected exposures; see paragraph 0049).
Regarding claim 11, Frosio and Liu disclose everything claimed as applied above (see claim 9). In addition, Frosio discloses the step of applying the hallucination technique is performed only for a first set of images of the first sequence, and wherein the method further comprises reprojecting a fourth set of images, generated upon applying the hallucination technique on the images of the first set of the first sequence, from a perspective of the second camera, wherein the reprojected fourth set of images is utilized when implementing the step of generating the output sequence of HDR images corresponding to the second camera (The system 565 includes stereoscopic camera systems; see paragraph 0100. Generating the set of exposure transformed images from the single input image 101 and then fusing the set of exposure transformed images to produce an exposure corrected output image 105; see paragraph 0023).
Regarding claim 12, Frosio and Liu disclose everything claimed as applied above (see claim 1). In addition, Frosio discloses the step of applying the hallucination technique on the one or more images is performed by employing a second neural network (Processor PPU 400 implementing a neural network model and the NVLink 410 interconnect enables systems to scale and include multiple PPUs 400 combined with one or more CPUs, supports cache coherence between the PPUs 400 and CPUs, and CPU mastering; see paragraphs 0052, 0056, 0033 and figs. 4, 5A).
Regarding claim 15, Frosio and Liu disclose everything claimed as applied above (see claim 1). In addition, Frosio discloses the images of the input sequence are received in a raw data format, and wherein one or more processing steps of the method are performed in a raw data domain (The images are first converted to an approximate linear domain, then linearly combined to change the exposure time, and then converted back to a tone mapped natural domain; see paragraph 0035).
Regarding claim 16, Frosio discloses a system for multi-exposure high dynamic range (HDR) imaging (see figs. 1A-1C, 3A), wherein the system comprises:
at least one camera (Cameras; see paragraphs 0052, 0082, 0100); and
at least one processor (Processor PPU 400; see paragraphs 0085, 0052, 0112 and fig. 4) configured to:
receive an input sequence of images by the at least one camera (Input image 101; see figs. 1A-2B. The input image is a frame of a video sequence and the process is repeated for additional input images included in the video sequence; see paragraphs 0017, 0049. Images provided by cameras; see paragraphs 0052, 0082, 0100), wherein the images of the input sequence are captured using one or more exposures (The training dataset includes images of many different scenes and, for each image, a set of M different exposure versions of the image is captured; see paragraph 0035);
apply a hallucination technique on one or more images of the input sequence, for generating a hallucinated set of images corresponding to a target exposure that lies within a target exposure range (Using large training datasets enables the image encoder 110, decoder 120, and image synthesis controller 115 to hallucinate and change the exposure levels in over- or under-exposed regions from a single input image. Controller 115 processes the latent representation to compute target (desired) enhancements that correspond to the exposure levels for synthesizing the set of exposure transformed images; see paragraphs 0033, 0027); and
generate an output sequence of HDR images at a same frame rate with which the input sequence is captured, by employing a first neural network (The method 300 shown in fig. 3A is implemented a processor PPU 400 implementing a neural network model; see paragraphs 0085, 0052, 0112. The process is repeated for additional input images included in the video sequence; see paragraphs 0017, 0049), each HDR image in the output sequence being generated using one of: a corresponding image from the hallucinated set, a corresponding image from the input sequence (One or more of the exposure transformed images are then merged to produce the output image 105; see fig. 1A and paragraph 0022. First, the synthesized transformations are apply to the input image to produce a set of exposure transformed images, then the output image is generated; see figs. 1A-1C, 3A and paragraphs 0049, 0028).
However, Frosio does not expressly disclose each HDR image in the output sequence being generated using at least a previously-generated HDR image of the output sequence.
On the other hand, Liu discloses each HDR image in the output sequence being generated using at least a previously-generated HDR image of the output sequence and one of: a corresponding image from the hallucinated set, a corresponding image from the input sequence (Given a few HDR key-frames and an LDR video, the TPN system 200 propagates task-specific data comprising scene radiance information from the key-frames to the remaining frames. The HDR information is propagated from a few HDR images input to the TPN system 200 to neighboring LDR frames. Therefore, the TPN system 200 provides an alternative solution for efficient, low cost HDR video reconstruction from a few provided HDR frames; see paragraphs 0070-0080 and figs. 2A-2B. The property data for the key-frame is high dynamic range data corresponding to the key-frame and the property data for the frame comprises high dynamic range data corresponding to the frame; see paragraph 0075).
Therefore, 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 teachings of Frosio and Liu to provide generate an output sequence of HDR images, by employing a first neural network, each HDR image in the output sequence being generated using at least a previously-generated HDR image of the output sequence and one of: a corresponding image from the hallucinated set, a corresponding image from the input sequence for the purpose of providing an efficient low cost HDR video reconstruction output.
7. Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Frosio in view of Liu and further in view of Nadesan et al. (US-PGPUB 2025/0166328).
Regarding claim 3, Frosio and Liu disclose everything claimed as applied above (see claim 2). However, Frosio fails to expressly disclose the predefined threshold lies in a range of -1 exposure value (EV) to 1 EV.
On the other hand, Nadesan discloses the predefined threshold lies in a range of -1 exposure value (EV) to 1 EV (Determining light data can include determining HDR data for the scene by: sampling an image of a collectively-illuminated region of the scene and locking the camera settings used to sample the image to establish a fixed 0-1 exposure range; see paragraphs 0015, 0095, 0097).
Therefore, 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 teachings of Frosio, Liu and Nadesan to provide the predefined threshold lies in a range of -1 exposure value (EV) to 1 EV for the purpose of avoiding clipping beyond 1 to preserve recoverable data.
8. Claims 13-14 are rejected under 35 U.S.C. 103 as being unpatentable over Frosio in view of Liu and further in view of Sehnert et al. (US-PGPUB 2023/0306657).
Regarding claim 13, Frosio and Liu disclose everything claimed as applied above (see claim 12). However, Frosio fails to expressly disclose the second neural network applies an effective exposure ratio to increase exposure in the images of the hallucinated set, the effective exposure ratio being a ratio of the target exposure to one or more exposures of the one or more images, and wherein the effective exposure ratio lies in a range of 2 to 64.
Nevertheless, Sehnert discloses the effective exposure ratio being a ratio of the target exposure to one or more exposures of the one or more images, and wherein the effective exposure ratio lies in a range of 2 to 64 (Low dose images are generated using long exposure times or averaging a number of short exposure images. To achieve noise reduction when implementing neural networks in composite images, a controlled exposure ratio between long and short exposure images is used. Preferred exposure ratios range between 2 and 10 are used; see paragraphs 0064, 0008).
Therefore, 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 teachings of Frosio, Liu and Sehnert to provide the second neural network applies an effective exposure ratio to increase exposure in the images of the hallucinated set, the effective exposure ratio being a ratio of the target exposure to one or more exposures of the one or more images, and wherein the effective exposure ratio lies in a range of 2 to 64 for the purpose of effectively achieving noise reduction in the high dynamic composite image.
Regarding claim 14, Frosio, Liu and Sehnert disclose everything claimed as applied above (see claim 13). In addition, Frosio discloses determining at least one of: a region of interest in the one or more images, based on gaze-tracking data collected by a gaze tracker, lighting conditions in the one or more images, based on at least one of: an image analysis technique, sensor data collected by a light sensor arranged in an operational environment of the at least one camera; and selecting the effective exposure ratio based on the at least one of: the region of interest, the lighting conditions (When the target brightness defined by the target enhancements is set to 0.7, pixels in the set of exposure transformed images are weighted according to the distance of their brightness from 0.7. The exposure fusion unit 220 learns to preserve very dark and very bright pixels in the input image which minimizes noise amplification and color distortion and also preserves the global dynamic range of the input image. The additional weight channel gives more weight to “very dark” or “very bright” pixels in the output image; see paragraphs 0038-0039).
Contact Information
9. Any inquiry concerning this communication or earlier communications from the examiner should be directed to CYNTHIA CALDERON whose telephone number is (571)270-3580. The examiner can normally be reached M-F 9:00 AM-5:00 PM.
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, TWYLER HASKINS can be reached at (571)272-7406. 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.
/CYNTHIA CALDERON/Primary Examiner, Art Unit 2639 09/04/2026
Prosecution Insights