no code implementations • 13 Feb 2022 • Jiayang Bai, Jie Guo, Chenchen Wan, Zhenyu Chen, Zhen He, Shan Yang, Piaopiao Yu, Yan Zhang, Yanwen Guo
At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view.
no code implementations • ICCV 2021 • Piaopiao Yu, Jie Guo, Fan Huang, Cheng Zhou, Hongwei Che, Xiao Ling, Yanwen Guo
However, naively compressing an outdoor panorama into a low-dimensional latent vector, as existing models have done, causes two major problems.