US 12,340,490 B2
Image processing method and apparatus
Zhen Huang, Dongguan (CN); and Qiao Li, Dongguan (CN)
Assigned to VIVO MOBILE COMMUNICATION CO., LTD., Dongguan (CN)
Filed by VIVO MOBILE COMMUNICATION CO., LTD., Dongguan (CN)
Filed on Nov. 16, 2022, as Appl. No. 17/987,987.
Application 17/987,987 is a continuation of application No. PCT/CN2021/093754, filed on May 14, 2021.
Claims priority of application No. 202010435861.8 (CN), filed on May 21, 2020.
Prior Publication US 2023/0076026 A1, Mar. 9, 2023
Int. Cl. G06T 5/80 (2024.01); G06N 3/045 (2023.01)
CPC G06T 5/80 (2024.01) [G06N 3/045 (2023.01); G06T 2207/20084 (2013.01)] 15 Claims
OG exemplary drawing
 
1. An image processing method, comprising:
acquiring a target image including a shadow; and
removing the shadow from the target image based on a target model, to acquire an image after shadow removal,
wherein the target model is a model trained based on a target image sample including a shadow and a shadow image sample corresponding to the target image sample,
wherein the target image sample is a sample generated in a three-dimensional rendering engine based on a captured shadow-free image sample and a preset emulated imaging condition, and the shadow image sample is a sample determined based on the target image sample and the shadow-free image sample and the preset emulated imaging condition comprises an imaging device, a preset obstruction, a preset emulated light source, a preset atmospheric environment, and an imaging plane;
wherein the target image sample is generated by creating a basic environment in the three-dimensional rendering engine, adding the imaging device, the preset obstruction, the preset emulated light source, the preset atmospheric environment, and the imaging plane, adding the shadow-free image sample into the imaging plane, randomly modifying influencing factors of the imaging device, imaging degree of the preset obstruction, parameters of the preset emulated light source, parameters of the preset atmospheric environment and influencing factors of the imaging plane, starting a renderer for rendering.
 
6. An electronic device, comprising:
a processor; and
a memory storing a computer program that is executable on the processor, wherein the computer program, when executed by the processor, causes the electronic device to perform the following steps:
acquiring a target image including a shadow; and
removing the shadow from the target image based on a target model, to acquire an image after shadow removal,
wherein the target model is a model trained based on a target image sample including a shadow and a shadow image sample corresponding to the target image sample,
wherein the target image sample is a sample generated in a three-dimensional rendering engine based on a captured shadow-free image sample and a preset emulated imaging condition, and the shadow image sample is a sample determined based on the target image sample and the shadow-free image sample and the preset emulated imaging condition comprises an imaging device, a preset obstruction, a preset emulated light source, a preset atmospheric environment, and an imaging plane;
wherein the target image sample is generated by creating a basic environment in the three-dimensional rendering engine, adding the imaging device, the preset obstruction, the preset emulated light source, the preset atmospheric environment, and the imaging plane, adding the shadow-free image sample into the imaging plane, randomly modifying influencing factors of the imaging device, imaging degree of the preset obstruction, parameters of the preset emulated light source, parameters of the preset atmospheric environment and influencing factors of the imaging plane, starting a renderer for rendering.
 
11. A non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, performs the following steps:
acquiring a target image including a shadow; and
removing the shadow from the target image based on a target model, to acquire an image after shadow removal, wherein the target model is a model trained based on a target image sample including a shadow and a shadow image sample corresponding to the target image sample,
wherein the target image sample is a sample generated in a three-dimensional rendering engine based on a captured shadow-free image sample and a preset emulated imaging condition, and the shadow image sample is a sample determined based on the target image sample and the shadow-free image sample and the preset emulated imaging condition comprises an imaging device, a preset obstruction, a preset emulated light source, a preset atmospheric environment, and an imaging plane;
wherein the target image sample is generated by creating a basic environment in the three-dimensional rendering engine, adding the imaging device, the preset obstruction, the preset emulated light source, the preset atmospheric environment, and the imaging plane, adding the shadow-free image sample into the imaging plane, randomly modifying influencing factors of the imaging device, imaging degree of the preset obstruction, parameters of the preset emulated light source, parameters of the preset atmospheric environment and influencing factors of the imaging plane, starting a renderer for rendering.