2022/11/25 by Jingwang Ling, Zhibo Wang, Ling, Jingwang +3
Computer Science · #Advanced Vision and Imaging #Artificial intelligence #Code (set theory) #Computer Graphics and Visualization Techniques #Computer Vision and Pattern Recognition (cs.CV) #Computer graphics (images) #Computer science #Computer vision #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #RGB color model #Representation (politics) #Shadow (psychology)
paper · pdf · doi:10.48550/arxiv.2211.14086
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2022/11/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
By supervising camera rays between a scene and multi-view image planes, NeRF reconstructs a neural scene representation for the task of novel view synthesis. On the other hand, shadow rays between the light source and the scene have yet to be considered. Therefore, we propose a novel shadow ray supervision scheme that optimizes both the samples along the ray and the ray location. By supervising shadow rays, we successfully reconstruct a neural SDF of the scene from single-view images under multiple lighting conditions. Given single-view binary shadows, we train a neural network to reconstruct a complete scene not limited by the camera's line of sight. By further modeling the correlation between the image colors and the shadow rays, our technique can also be effectively extended to RGB inputs. We compare our method with previous works on challenging tasks of shape reconstruction from single-view binary shadow or RGB images and observe significant improvements. The code and data are available at https://github.com/gerwang/ShadowNeuS.