English

Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

Computer Vision and Pattern Recognition 2023-08-22 v2

Abstract

Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction. However, their implicit volumetric representations differ significantly from the widely-adopted polygonal meshes and lack support from common 3D software and hardware, making their rendering and manipulation inefficient. To overcome this limitation, we present a novel framework that generates textured surface meshes from images. Our approach begins by efficiently initializing the geometry and view-dependency decomposed appearance with a NeRF. Subsequently, a coarse mesh is extracted, and an iterative surface refining algorithm is developed to adaptively adjust both vertex positions and face density based on re-projected rendering errors. We jointly refine the appearance with geometry and bake it into texture images for real-time rendering. Extensive experiments demonstrate that our method achieves superior mesh quality and competitive rendering quality.

Keywords

Cite

@article{arxiv.2303.02091,
  title  = {Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement},
  author = {Jiaxiang Tang and Hang Zhou and Xiaokang Chen and Tianshu Hu and Errui Ding and Jingdong Wang and Gang Zeng},
  journal= {arXiv preprint arXiv:2303.02091},
  year   = {2023}
}

Comments

ICCV 2023 camera-ready, Project Page: https://me.kiui.moe/nerf2mesh

R2 v1 2026-06-28T09:00:13.324Z