Tootfinder

The most important lesson that one can learn about technology writ large. RTFM. @… https://eigenmagic.net/@daedalus/115839190423202974

Mesh Splatting for End-to-end Multiview Surface Reconstruction
Ruiqi Zhang, Jiacheng Wu, Jie Chen
https://arxiv.org/abs/2601.21400 https://arxiv.org/pdf/2601.21400 https://arxiv.org/html/2601.21400
arXiv:2601.21400v1 Announce Type: new
Abstract: Surfaces are typically represented as meshes, which can be extracted from volumetric fields via meshing or optimized directly as surface parameterizations. Volumetric representations occupy 3D space and have a large effective receptive field along rays, enabling stable and efficient optimization via volumetric rendering; however, subsequent meshing often produces overly dense meshes and introduces accumulated errors. In contrast, pure surface methods avoid meshing but capture only boundary geometry with a single-layer receptive field, making it difficult to learn intricate geometric details and increasing reliance on priors (e.g., shading or normals). We bridge this gap by differentiably turning a surface representation into a volumetric one, enabling end-to-end surface reconstruction via volumetric rendering to model complex geometries. Specifically, we soften a mesh into multiple semi-transparent layers that remain differentiable with respect to the base mesh, endowing it with a controllable 3D receptive field. Combined with a splatting-based renderer and a topology-control strategy, our method can be optimized in about 20 minutes to achieve accurate surface reconstruction while substantially improving mesh quality.
toXiv_bot_toot