Is Single-View Mesh Reconstruction Ready for Robotics?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nolte, Frederik, Geiger, Andreas, Schölkopf, Bernhard, Posner, Ingmar
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913983991119872
author Nolte, Frederik
Geiger, Andreas
Schölkopf, Bernhard
Posner, Ingmar
author_facet Nolte, Frederik
Geiger, Andreas
Schölkopf, Bernhard
Posner, Ingmar
contents This paper evaluates single-view mesh reconstruction models for their potential in enabling instant digital twin creation for real-time planning and dynamics prediction using physics simulators for robotic manipulation. Recent single-view 3D reconstruction advances offer a promising avenue toward an automated real-to-sim pipeline: directly mapping a single observation of a scene into a simulation instance by reconstructing scene objects as individual, complete, and physically plausible 3D meshes. However, their suitability for physics simulations and robotics applications under immediacy, physical fidelity, and simulation readiness remains underexplored. We establish robotics-specific benchmarking criteria for 3D reconstruction, including handling typical inputs, collision-free and stable geometry, occlusions robustness, 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17966
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Is Single-View Mesh Reconstruction Ready for Robotics?
Nolte, Frederik
Geiger, Andreas
Schölkopf, Bernhard
Posner, Ingmar
Robotics
Computer Vision and Pattern Recognition
I.4.5; I.4.8; I.2.9; I.2.10
This paper evaluates single-view mesh reconstruction models for their potential in enabling instant digital twin creation for real-time planning and dynamics prediction using physics simulators for robotic manipulation. Recent single-view 3D reconstruction advances offer a promising avenue toward an automated real-to-sim pipeline: directly mapping a single observation of a scene into a simulation instance by reconstructing scene objects as individual, complete, and physically plausible 3D meshes. However, their suitability for physics simulations and robotics applications under immediacy, physical fidelity, and simulation readiness remains underexplored. We establish robotics-specific benchmarking criteria for 3D reconstruction, including handling typical inputs, collision-free and stable geometry, occlusions robustness, 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.
title Is Single-View Mesh Reconstruction Ready for Robotics?
topic Robotics
Computer Vision and Pattern Recognition
I.4.5; I.4.8; I.2.9; I.2.10
url https://arxiv.org/abs/2505.17966