VALSE 论文速览 第156期：Shadow Ray-Guided SDF Reconstruction

论文题目：

ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision

作者列表：

凌精望 (清华大学)、王至博 (商汤科技)、徐枫 (清华大学）

B站观看网址：

https://www.bilibili.com/video/BV1Xe411b7dc/

论文摘要：

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.

参考文献：

[1] Jingwang Ling, Zhibo Wang, Feng Xu, "ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision", IEEE/ CVF International Conference on Computer Vision and Pattern Recognition (CVPR) 2023

论文链接：

[https://arxiv.org/abs/2211.14086]

代码链接：

[https://github.com/gerwang/ShadowNeuS]

视频讲者简介：

凌精望，清华大学软件学院博士生。主要研究逆向渲染和三维人脸动画。

个人主页：

https://gerwang.github.io/

特别鸣谢本次论文速览主要组织者：

月度轮值AC：李爽 (北京理工大学)

季度轮值AC：樊彬 (北京科技大学)