English

GMLight: Lighting Estimation via Geometric Distribution Approximation

Computer Vision and Pattern Recognition 2022-03-23 v2

Abstract

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 poor accuracy and generalization. This paper presents Geometric Mover's Light (GMLight), a lighting estimation framework that employs a regression network and a generative projector for effective illumination estimation. We parameterize illumination scenes in terms of the geometric light distribution, light intensity, ambient term, and auxiliary depth, which can be estimated by a regression network. Inspired by the earth mover's distance, we design a novel geometric mover's loss to guide the accurate regression of light distribution parameters. With the estimated light parameters, the generative projector synthesizes panoramic illumination maps with realistic appearance and high-frequency details. Extensive experiments show that GMLight achieves accurate illumination estimation and superior fidelity in relighting for 3D object insertion. The codes are available at \href{https://github.com/fnzhan/Illumination-Estimation}{https://github.com/fnzhan/Illumination-Estimation}.

Keywords

Cite

@article{arxiv.2102.10244,
  title  = {GMLight: Lighting Estimation via Geometric Distribution Approximation},
  author = {Fangneng Zhan and Yingchen Yu and Changgong Zhang and Rongliang Wu and Wenbo Hu and Shijian Lu and Feiying Ma and Xuansong Xie and Ling Shao},
  journal= {arXiv preprint arXiv:2102.10244},
  year   = {2022}
}

Comments

11 pages, 12 figures

R2 v1 2026-06-23T23:20:51.490Z