GMLight: lighting estimation via geometric distribution approximation
Inferring the scene illumination from a single image is an essential yet challenging task in computer vision and computer graphics. Existing works estimate lighting by regressing representative illumination parameters or generating illumination maps directly. However, these methods often suffer from...
Main Authors: | Zhan, Fangneng, Yu, Yingchen, Zhang, Changgong, Wu, Rongliang, Hu, Wenbo, Lu, Shijian, Ma, Feiying, Xie, Xuansong, Shao, Ling |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/157035 |
Similar Items
-
POCE: pose-controllable expression editing
by: Wu, Rongliang, et al.
Published: (2024) -
LEED : label-free expression editing via disentanglement
by: Wu, Rongliang, et al.
Published: (2021) -
Defect-GAN : high-fidelity defect synthesis for automated defect inspection
by: Zhang, Gongjie, et al.
Published: (2021) -
Image processing of robotic eyes
by: Deng, Xin
Published: (2013) -
Approximating arrival costs in distributed moving horizon estimation: a recursive method
by: Li, Xiaojie, et al.
Published: (2024)