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 .
Application Status
This office action is responsive to the amendments filed on 02/13/2026.
The previous 35 USC 101 Rejection has been withdrawn in view of the Applicant’s amendments.
This action has been made FINAL.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55 (Foreign Priority Date: 03/24/2021).
Response to Arguments
Applicant's arguments filed 02/13/2026 have been fully considered but they are not persuasive.
The Applicant alleged the following: “The Examiner alleges that Kaplanyan teaches every element previously recited by independent claim 1. Office Action 6-8 (citing Kaplanyan Abstract, col. 1, lines 59-67, col. 9, lines 10-20). However, there is nothing in Kaplanyan that would fairly teach or suggest the elements presently recited in relation to rendering model data by a method different from a ray tracing method to create an additional video with a higher sampling rate or a higher resolution than the ray traced video, and synthesizing the additional video and the ray traced video to create a synthesized video, let alone any teaching or suggestion to creating the ray traced video and the additional video simultaneously and the synthesized video being created according to a learned coefficient of a neural network, let alone in anything remotely resembling the manner particularly claimed. As such, it is simply not possible for Kaplanyan to satisfy the elements particularly recited by amended independent claim 1.”. The examiner is not persuaded. Because "applicants may amend claims to narrow their scope, a broad construction during prosecution creates no unfairness to the applicant or patentee." In re ICON Health and Fitness, Inc., 496 F.3d 1374, 1379 (Fed. Cir. 2007) (citing In re Am. Acad. of Sci. Tech Ctr., 367 F.3d 1359, 1364 (Fed. Cir. 2004)). The combination of Kaplanyan and JANUS discloses the Applicant’s claim lanague of “synthesize the additional video and the ray traced video and to create a synthesized video wherein the ray traced video and the additional video are created simultaneously and synthesized” in Kaplanyan Column 9, Lines 10-20. JANUS discloses the Applicant’s claim lanague of “according to a learned coefficient of a neural network” in Paragraph 0225.
MPEP § 2106 states Office personnel are to give claims their broadest reasonable interpretation in light of the supporting disclosure. In re Morris, 127 F.3d 1048, 1054-55, 44 USPQ2d 1023, 1027-28 (Fed Cir. 1997). Accordingly, the examiner maintains the rejection.
The Applicant alleged the following: “In reply to the rejection of claims 7, 8, 11, and 15 under 35 U.S.C. §103 as allegedly being unpatentable over Kaplanyan in view of Dammertz, Applicant respectfully requests reconsideration.” The examiner is not persuaded. The Applicant is rehashing arguments already address previously (See Above Response). Accordingly, the examiner maintains the rejection.
The Applicant alleged the following: “In reply to the rejection of claims 0 and 12 under 35 U.S.C. §103 as allegedly being unpatentable over Kaplanyan in view of Bakalash, Applicant respectfully requests reconsideration.” The examiner is not persuaded. The Applicant is rehashing arguments already address previously (See Above Response). Accordingly, the examiner maintains the rejection.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-6, 9, 13, 14, 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Kaplanyan, US 11037531 in view of JANUS, US 20200211264.
Claim 1:
Kaplanyan discloses an information processing apparatus (See Kaplanyan Abstract).
Kaplanyan failed to disclose a learned coefficient of a neural network however, Janus disclosed this feature in Paragraph 0225. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Kaplanyan by the teachings of JANUS to perform more efficient ray tracing operations, more effectively (See JANUS Field of the Invention). In addition, both of the references teach features that are directed to analogous art and they are directed to the same field of endeavor, such as ray tracing. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Kaplanyan and JANUS discloses the following:
circuitry configured to
render model data (See Kaplanyan Column 1, Lines 59-671) by a ray tracing method and to create a ray traced video (See Kaplanyan Column 1, Lines 59-672), and
render the model data by a method different from the ray tracing method (See Kaplanyan Column 1, Lines 59-673) and to create an additional video (See Kaplanyan Column 1, Lines 59-674) with at least one of a higher sampling rate or a higher resolution (See Kaplanyan Column 7, Lines 32-455) than the ray traced video (See Kaplanyan Column 1, Lines 59-676);
synthesize the additional video and the ray traced video and to create a synthesized video wherein the ray traced video and the additional video are created simultaneously and synthesized (See Kaplanyan Column 9, Lines 10-207) according to a learned coefficient of a neural network (See Janus Paragraph 0225).
Claim 2:
The combination of Kaplanyan and JANUS discloses wherein the circuitry renders the model data for every N frames by the ray tracing method (See Kaplanyan Column 1, Lines 59-67), temporally thins out the model data, and creates the ray traced video (See Kaplanyan Column 1, Lines 59-678), wherein circuitry is further configured to calculate a motion vector from the N frame to a thinned-out frame based on an additional video of the N frame and an additional video of the thinned-out frame (See Kaplanyan Column 10, Lines 45-67), the thinned-out frame being a frame for which a ray traced video is not created (See Kaplanyan Column 10, Lines 45-67), and wherein the circuitry synthesizes (See Kaplanyan Column 9, Lines 10-209) the additional video of the thinned-out frame and a corrected ray traced video created by correcting the ray traced video of the N frame based on the motion vector (See Kaplanyan Column 10, Lines 45-67), and creates the synthesized video of the thinned-out frame (See Kaplanyan Column 9, Lines 10-2010).
Claim 3:
The combination of Kaplanyan and JANUS discloses wherein the circuitry is further configured to correct ray traced video (See Kaplanyan Column 1, Lines 59-67; Column 4, Lines 1-511).
Claim 4:
The combination of Kaplanyan and JANUS discloses wherein the circuitry (See Kaplanyan Column 9, Lines 10-2012) creates the corrected ray traced video (See Kaplanyan Column 1, Lines 59-67; Column 4, Lines 1-513).
Claim 5:
The combination of Kaplanyan and JANUS discloses wherein the circuitry is further configured to set a representation region unique to the ray tracing method of the model data (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20), wherein the circuitry renders the representation region of the model data by the ray tracing method and to create the ray traced video (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20), and wherein the circuitry (See Kaplanyan Column 9, Lines 10-2014) synthesizes the additional video (See Kaplanyan Column 1, Lines 59-6715) and the ray traced video of the representation region and to create the synthesized video (See Kaplanyan Column 9, Lines 10-20).
Claim 6:
The combination of Kaplanyan and JANUS discloses wherein the circuitry creates a mask video for masking (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20) the representation region based on a material setting of the model data, and wherein the circuitry sets the representation region specified by the mask video (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20).
Claim 9:
The combination of Kaplanyan and JANUS discloses wherein the circuitry sets a rendering parameter used when the representation region is rendered by the ray tracing method (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20), and wherein the circuitry renders the representation region of the model data by the ray tracing method (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20) based on the rendering parameter and to create the ray traced video (See Kaplanyan Column 1, Lines 59-67).
Claim 13:
The combination of Kaplanyan and JANUS discloses wherein the circuitry further creates, as the additional video (See Kaplanyan Column 1, Lines 59-6716), an internal component including at least one of an Albedo component, a normal component, a depth component (See Kaplanyan Column 16, Lines 55-60), a roughness component, a UV map component, an arbitrary output variables (AOVs) component, or a shadow map component of the additional video (See Kaplanyan Column 16, Lines 55-60).
Claim 14:
The combination of Kaplanyan and JANUS discloses wherein the ray tracing method is includes at least one of ray tracing or path tracing (See Kaplanyan Column 1, Lines 59-6717).
Claim 16:
Claim 16 is rejected on the same basis as claim 1.
Claim 17:
Claim 17 is rejected on the same basis as claim 1.
Claim(s) 7, 8, 11 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Kaplanyan, US 11037531, JANUS, US 20200211264 and in view of DAMMERTZ, US 20100053162.
Claim 7:
Kaplanyan and JANUS failed to disclose samples per pixel (SPP), however, DAMMERTZ discloses this feature in paragraph 0145. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Kaplanyan by the teachings of DAMMERTZ to enable computer graphics systems to accurately and efficiently render images, more effectively. (See DAMMERTZ Summary of the Invention). In addition, both of the references teach features that are directed to analogous art and they are directed to the same field of endeavor, such as ray tracing. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Kaplanyan, JANUS and DAMMERTZ discloses the following:
wherein the circuitry pre-renders the model data by a ray tracing method (See Kaplanyan Column 1, Lines 59-67) of at least one of lower samples per pixel (SPP) (See DAMMERTZ Paragraph 0145) or lower resolution than that of the ray tracing method and to create a pre-rendered video, and creates a mask video (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20) for masking the representation region based on an internal component of the pre-rendered video, and wherein the circuitry sets the representation region specified by the mask video (See Kaplanyan Figure 5, Item 520; Column 8, Lines 1-20).
Claim 8:
The combination of Kaplanyan, JANUS and DAMMERTZ discloses the following:
wherein the circuitry pre-renders the model data by a ray tracing method (See Kaplanyan Column 1, Lines 59-6718) of at least one of lower samples per pixel (SPP) (See DAMMERTZ Paragraph 0145) or lower resolution than that of the ray tracing method and to create a pre-rendered video (See Kaplanyan Column 1, Lines 59-6719), wherein the circuitry is further configured to discriminate (See Kaplanyan Column 9, Lines 20-42) the representation region from the pre-rendered video created by the circuitry (See Kaplanyan Column 1, Lines 59-67), and wherein the circuitry sets the representation region predicted from the pre-rendered video (See Kaplanyan Column 10, Lines 65-67 wherein Kaplanyan teachings of “estimated dense frame” is the same as the Applicant’s recitation of “predicted”).
Claim 11:
The combination of Kaplanyan, JANUS and DAMMERTZ discloses the following:
wherein the circuitry renders the model data by a non-ray tracing method or a ray tracing method (See Kaplanyan Column 1, Lines 59-6720) at least one of lower samples per pixel (SPP) (See DAMMERTZ Paragraph 0145) or lower resolution than that of the ray tracing method (See Kaplanyan Column 1, Lines 59-6721), as a method different from the ray tracing method, and creates the additional video (See Kaplanyan Column 1, Lines 59-67).
Claim 15:
The combination of Kaplanyan, JANUS and DAMMERTZ discloses the following:
wherein the circuitry renders the model data by a ray tracing method (See Kaplanyan Column 1, Lines 59-6722) of SPP less than 16 SPP (See DAMMERTZ Paragraph 0145) and to create the ray traced video (See Kaplanyan Column 1, Lines 59-6723).
Claim(s) 10 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Kaplanyan, US 11037531, JANUS, US 20200211264 and in view of Bakalash, US 20200058155.
Claim 10:
Kaplanyan and JANUS failed to disclose a ratio, however Bakalash discloses this feature in Paragraph 0022. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Kaplanyan and JANUS by the teachings of Bakalash to enable a new and improved way of carrying out ray tracing method at a reduced computational complexity (See Bakalash Field of the Invention). In addition, both of the references teach features that are directed to analogous art and they are directed to the same field of endeavor, such as ray tracing. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Kaplanyan, JANUS and Bakalash discloses the following:
wherein the circuitry sets the rendering parameter based on a ratio of the representation region to an entire region of the ray traced video (See Bakalash Paragraphs 0018-0022).
Claim 12:
Kaplanyan and JANUS, failed to disclose a rasterization method, however Bakalash discloses this feature in Paragraphs 0018-0022. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have further modified Kaplanyan and JANUS by the teachings of Bakalash’s rasterization method, by enabling a new and improved way of carrying out ray tracing method at a reduced computational complexity (See Bakalash Field of the Invention). In addition, both of the references teach features that are directed to analogous art and they are directed to the same field of endeavor, such as ray tracing. This close relation between both of the references highly suggests an expectation of success.
As modified:
The combination of Kaplanyan, JANUS and Bakalash discloses the following:
wherein the non-ray tracing method includes at least one of a rasterization method, a Z-sorting method, a Z-buffer method, or a scanline method (See Bakalash Paragraphs 0018-0022).
Pertinent Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US 20200074089 enables compositing operations that directly access and modify data from a ray tracing renderer, prior to rasterizing an image into pixels.
US 20180150994 generated 3-dimensional video images, and more particularly, to systems, methods, and computer-readable storage media that generates geo-registered 3-dimensional video objects and textures the 3-dimensional video objects with 2-dimensional video images.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SHEREE N BROWN whose telephone number is (571)272-4229. The examiner can normally be reached M-F 5:30-2:00 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, SAID BROOME can be reached at (571) 272-2931. 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.
/SHEREE N BROWN/Primary Examiner, Art Unit 2612 May 2, 2026
1 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
2 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
3 The prior art reference, Kaplanyan mentions “ray casting, or other physics-based computer-graphics techniques” which is equivalent to the Applicants claim language of “renders the model data by a method different from the ray tracing method”. Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
4 The prior art reference, Kaplanyan mentions “generating video frames”, in which frames is plural, indicating a plurality of video frames. Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
5 Kaplanyan Column 7, Lines 32-45 recites “the sampling rate R(x)∈[0; 1] based on the maximum perceptible frequency.” Note: The examiner interprets “higher” as being the same as “maximum.”
6 The prior art reference, Kaplanyan mentions “ray casting, or other physics-based computer-graphics techniques” which is equivalent to the Applicants claim language of “renders the model data by a method different from the ray tracing method”. Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
7 Kaplanyan Column 9, Lines 10-20 recites “Deep learning algorithms continually show results of unprecedented quality in the realm of image synthesis and analysis. Due to their fixed-function pipeline, they are highly amenable to execution on hardware. Therefore, they are a natural choice for the problem at hand.”
8 The prior art reference, Kaplanyan mentions “ray casting, or other physics-based computer-graphics techniques” which is equivalent to the Applicants claim language of “renders the model data by a method different from the ray tracing method”. Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
9 Kaplanyan Column 9, Lines 10-20 recites “Deep learning algorithms continually show results of unprecedented quality in the realm of image synthesis and analysis. Due to their fixed-function pipeline, they are highly amenable to execution on hardware. Therefore, they are a natural choice for the problem at hand.”
10 Kaplanyan Column 9, Lines 10-20 recites “Deep learning algorithms continually show results of unprecedented quality in the realm of image synthesis and analysis. Due to their fixed-function pipeline, they are highly amenable to execution on hardware. Therefore, they are a natural choice for the problem at hand.”
11 Kaplanyan teaching of “reconstruct the full video frame” is the same as the Applicant’s claim language of “corrected ray traced video”.
12 Kaplanyan Column 9, Lines 10-20 recites “Deep learning algorithms continually show results of unprecedented quality in the realm of image synthesis and analysis. Due to their fixed-function pipeline, they are highly amenable to execution on hardware. Therefore, they are a natural choice for the problem at hand.”
13 Kaplanyan teaching of “reconstruct the full video frame” is the same as the Applicant’s claim language of “corrected ray traced video”.
14 Kaplanyan Column 9, Lines 10-20 recites “Deep learning algorithms continually show results of unprecedented quality in the realm of image synthesis and analysis. Due to their fixed-function pipeline, they are highly amenable to execution on hardware. Therefore, they are a natural choice for the problem at hand.”
15 The prior art reference, Kaplanyan mentions “generating video frames”, in which frames is plural, indicating a plurality of video frames. Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
16 The prior art reference, Kaplanyan mentions “generating video frames”, in which frames is plural, indicating a plurality of video frames. Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
17 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
18 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
19 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
20 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
21 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
22 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
23 Kaplanyan Column 1, Lines 59-67 recites “generating and/or compressing and reconstructing perceptively-accurate images (e.g., including video frames) based on a sequence of video frames with incomplete pixel information (e.g., sparse sample datasets of pixel color for the frames). Since perceptively-accurate images can be generated from sparse sample datasets using machine learning, the computationally more expensive rendering pipeline (e.g., using ray tracing, ray casting, or other physics-based computer-graphics techniques) may only be needed for a sparse subset of the total pixels in the image.”
Prosecution Insights