Physics Based Differentiable Rendering for Inverse Problems and Beyond
This is an incremental review paper summarizing existing methods for applications such as autonomous navigation and scene reconstruction, without introducing novel solutions.
The paper provides an overview of physics-based differentiable rendering (PBDR) techniques, which tackle inverse problems in computer vision and graphics by generating patterns from perceptions to enhance object attributes like geometry and lighting, but it does not present new results or concrete numbers.
Physics-based differentiable rendering (PBDR) has become an efficient method in computer vision, graphics, and machine learning for addressing an array of inverse problems. PBDR allows patterns to be generated from perceptions which can be applied to enhance object attributes like geometry, substances, and lighting by adding physical models of light propagation and materials interaction. Due to these capabilities, distinguished rendering has been employed in a wider range of sectors such as autonomous navigation, scene reconstruction, and material design. We provide an extensive overview of PBDR techniques in this study, emphasizing their creation, effectiveness, and limitations while managing inverse situations. We demonstrate modern techniques and examine their value in everyday situations.