Is Single-View Mesh Reconstruction Ready for Robotics?
Is Single-View Mesh Reconstruction Ready for Robotics?
This paper evaluates single-view mesh reconstruction models for creating digital twin environments in robot manipulation. Recent advances in computer vision for 3D reconstruction from single viewpoints present a potential breakthrough for efficiently creating virtual replicas of physical environments for robotics contexts. However, their suitability for physics simulations and robotics applications remains unexplored. We establish benchmarking criteria for 3D reconstruction in robotics contexts, including handling typical inputs, producing collision-free and stable reconstructions, managing occlusions, and meeting computational constraints. Our empirical evaluation using realistic robotics datasets shows that despite success on computer vision benchmarks, existing approaches fail to meet robotics-specific requirements. We quantitively examine limitations of single-view reconstruction for practical robotics implementation, in contrast to prior work that focuses on multi-view approaches. Our findings highlight critical gaps between computer vision advances and robotics needs, guiding future research at this intersection.
Frederik Nolte、Bernhard Sch?lkopf、Ingmar Posner
计算技术、计算机技术
Frederik Nolte,Bernhard Sch?lkopf,Ingmar Posner.Is Single-View Mesh Reconstruction Ready for Robotics?[EB/OL].(2025-05-23)[2025-07-09].https://arxiv.org/abs/2505.17966.点此复制
评论