# US 2021/0243426 A1 · Method for generating multi-view images from a single image > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0243426 A1 - Document ID: US20210243426A1 - Status: Published application - Kind: A1 - Application number: 17/234,307 - Filed: 2021-04-19 - Published: 2021-08-05 - Earliest claimed: 2013-01-14 - Assignees: City University of Hong Kong - Applicants: City University of Hong Kong - Inventors: Peter Wai Ming TSANG - Web page: https://patentgrep.com/patent/US20210243426A1 ## CPC - H04N 13/302: for viewing without the aid of special glasses, i.e. using autostereoscopic displays - G06T 15/205: {Image-based rendering} - G06T 17/00: Three-dimensional [3D] modelling for computer graphics - G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics - H04N 13/261: with monoscopic-to-stereoscopic image conversion - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract From only a single two-dimensional source image (20) of a scene, multiple images (28) of the scene are generated, wherein each image is from a different viewing direction or angle. For each of the multiple images, a disparity is generated corresponding to the viewing direction and combined with significant pixels (e.g., edge detected pixels) in the source image. The disparity may be filtered (26) (e.g., low-pass filtered) prior to combined with the significant pixels. The multiple images are combined into an integrated image for display, for example, on an auto stereoscopic monitor (10). The process can be repeated on multiple related source images to create a video sequence. ## Claims ### Claim 1 A method of generating a plurality of multi-view images of a scene, the method comprising: obtaining a single two-dimensional source image of a scene, the source image comprising a plurality of source pixels (20); automatically generating at least two multi-view images (28) of the scene from less than all of the plurality of source pixels, each of the at least two multi-view images having a different viewing direction for the scene, wherein each of the at least two multi-view images includes no portion of the single two-dimensional source image; integrating (64) the at least two multi-view images (60), prior to displaying, by combining an entirety of each of the at least two multi-view images into a single integrated image of the scene (62); and displaying, after the integrating, the single integrated image on a three-dimensional multi-view autostereoscopic display. ### Claim 2 (depends on 1) The method of claim 1, wherein the automatically generating comprises, for each of the at least two multi-view images (28), generating a disparity (24) for each of the at least some of the plurality of source pixels. ### Claim 3 (depends on 2) The method of claim 2, wherein the disparity comprises weighted values for each of red, blue and green colors. ### Claim 4 (depends on 2) The method of claim 2, wherein the automatically generating further comprises, for each of the at least two multi-view images (28), adding the generated disparity to each of the at least some of the plurality of source pixels. ### Claim 5 (depends on 4) The method of claim 4, wherein the automatically generating further comprises, prior to the combining, filtering (26) to create a filtered disparity (27), and wherein the combining comprises combining the filtered disparity with each of the at least some of the plurality of source pixels (20). ### Claim 6 (depends on 5) The method of claim 5, wherein the filtering comprises low-pass filtering. ### Claim 7 (depends on 1) The method of claim 1, wherein the automatically generating comprises identifying (35) the less than all of the plurality of source pixels based on predetermined criteria. ### Claim 8 (depends on 7) The method of claim 7, wherein the identifying comprises edge detection. ### Claim 9 (depends on 1) The method of claim 1, further comprising repeating the obtaining and the automatically generating for a series of related images of the scene to create a video sequence. ### Claim 10 A computing unit (50), comprising: a memory (56); and a processor (52) in communication with the memory for generating a plurality of multi-view images of a scene according to a method, the method comprising: obtaining a single two-dimensional source image of a scene, the source image comprising a plurality of source pixels (20); automatically generating at least two multi-view images (28) of the scene from less than all of the plurality of source pixels, each of the at least two multi-view images having a different viewing direction for the scene, wherein each of the at least two multi-view images includes no portion of the single two-dimensional source image; integrating (64) the at least two multi-view images (60), prior to displaying, by combining an entirety of each of the at least two multi-view images into a single integrated image of the scene (62); and displaying, after the integrating, the single integrated image on a three-dimensional multi-view autostereoscopic display. ### Claim 11 (depends on 10) At least one hardware chip for generating a plurality of multi-view images of a scene according to the method of claim 10. ### Claim 12 (depends on 11) The at least one hardware chip of claim 11, wherein the at least one hardware chip comprises a Field Programmable Gate Array chip. ### Claim 13 A computer program product (40) for generating multi-view images of a scene, the computer program product comprising a non-transitory computer readable medium (42) readable by a processing circuit and storing instructions (44) for execution by the processing circuit for performing a method of generating a plurality of multi-view images of a scene, the method comprising: obtaining a single two-dimensional source image of a scene, the source image comprising a plurality of source pixels (20); automatically generating at least two multi-view images (28) of the scene from less than all of the plurality of source pixels, each of the at least two multi-view images having a different viewing direction for the scene, wherein each of the at least two multi-view images includes no portion of the single two-dimensional source image; integrating (64) the at least two multi-view images (60), prior to displaying, by combining an entirety of each of the at least two multi-view images into a single integrated image of the scene (62); and displaying, after the integrating, the single integrated image on a three-dimensional multi-view autostereoscopic display. ### Claim 14 (depends on 13) The computing unit of claim 13, wherein the automatically generating comprises, for each of the at least two multi-view images (28), generating a disparity (24) for each of the at least some of the plurality of source pixels. ### Claim 15 (depends on 13) The computing unit of claim 13, wherein the automatically generating comprises identifying the less than all of the plurality of source pixels based on predetermined criteria, and wherein the method further comprises repeating the obtaining and the automatically generating for a series of related images of the scene to create a video sequence. ### Claim 16 (depends on 13) The computer program product of claim 13, wherein the automatically generating comprises, for each of the at least two multi-view images (28), generating a disparity (24) for each of the at least some of the plurality of source pixels. ### Claim 17 (depends on 13) The computer program product of claim 13, wherein the automatically generating comprises identifying the less than all of the plurality of source pixels as having at least a predetermined level of relevance, and wherein the method further comprises repeating the obtaining and the automatically generating for a series of related images of the scene to create a video sequence.