Non-Line-of-Sight Reconstruction using Efficient Transient Rendering
This addresses the challenge of non-line-of-sight vision for applications like surveillance or robotics, presenting an incremental improvement over prior methods.
The paper tackled the problem of reconstructing objects beyond direct line-of-sight using time-resolved light measurements, introducing a method that combines an efficient forward model with optimization to handle noisy or non-diffuse scenes effectively.
Being able to see beyond the direct line of sight is an intriguing prospective and could benefit a wide variety of important applications. Recent work has demonstrated that time-resolved measurements of indirect diffuse light contain valuable information for reconstructing shape and reflectance properties of objects located around a corner. In this paper, we introduce a novel reconstruction scheme that, by design, produces solutions that are consistent with state-of-the-art physically-based rendering. Our method combines an efficient forward model (a custom renderer for time-resolved three-bounce indirect light transport) with an optimization framework to reconstruct object geometry in an analysis-by-synthesis sense. We evaluate our algorithm on a variety of synthetic and experimental input data, and show that it gracefully handles uncooperative scenes with high levels of noise or non-diffuse material reflectance.