Skip to content
arXiv cs.CV · Papers

MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding

arXiv:2512.12307v5 Announce Type: replace Abstract: While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D inputs, they are often assumed to