PhyRecon: Physically Plausible Neural Scene Reconstruction

arXiv:2404.16666v1 Announce Type: new
Abstract: While neural implicit representations have gained popularity in multi-view 3D reconstruction, previous work struggles to yield physically plausible results, thereby limiting their applications in physics-demanding domains like embodied AI and robotics. The lack of plausibility originates from both the absence of physics modeling in the existing pipeline and their inability to recover intricate geometrical structures. In this paper, we introduce PhyRecon, which stands as the first approach to harness both differentiable rendering and differentiable physics …

3d reconstruction abstract ai and robotics applications arxiv cs.cv domains embodied embodied ai modeling physics pipeline results robotics type view while work