Neural Inverse Rendering from Propagating Light

estimated normals lidar frames (novel views) direct component indirect component time-resolved relighting (novel views) 2.62 ns 2.96 ns 2.37 ns 2.86 ns conventional image Figure 1. We introduce a method to model and invert multi-view, time-resolved measurements of propagating light from a flash lidar system. (row 1) Our method accurately recovers the geometry of this scene and enables rendering of time-resolved lidar measurements that reveal light propagation from novel views. (row 2) Physically-based modeling enables novel applications, such as time-resolved relighting and automatic decomposition of light transport into direct and indirect components.