RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
Year: 2025
Type: preprint
Abstract: In this paper, we present a generalizable method for 3D surface reconstruction from raw point clouds or pre-estimated 3D Gaussians by 3DGS from RGB images. Unlike existing coordinate-based methods which are often computationally intensive when rendering explicit surfaces, our proposed method, named RayletDF, introduces a new technique called raylet distance field, which aims to directly predict surface points from query rays. Our pipeline consists of three key modules: a raylet feature extractor, a raylet distance field predictor, and a multi-raylet blender. These components work together to extract fine-grained local geometric features, predict raylet distances, and aggregate multiple predictions to reconstruct precise surface points. We extensively evaluate our method on multiple public real-world datasets, demonstrating superior performance in surface reconstruction from point clouds or 3D Gaussians. Most notably, our method achieves exceptional generalization ability, successfully recovering 3D surfaces in a single-forward pass across unseen datasets in testing.
Source: arXiv (Cornell University)
Authors: Wei, Shenxing, Li, Jinxi, Yang, Yafei, Zhou, Siyuan, Yang, Bo
Language: English
Subfield: Computational Mechanics
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979276254
Cites:
Cited by:
Related to: