{"ID":2882824,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.09830","arxiv_id":"2508.09830","title":"RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians","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.","short_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...","url_abs":"https://arxiv.org/abs/2508.09830","url_pdf":"https://arxiv.org/pdf/2508.09830v1","authors":"[\"Shenxing Wei\",\"Jinxi Li\",\"Yafei Yang\",\"Siyuan Zhou\",\"Bo Yang\"]","published":"2025-08-13T14:05:21Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.GR\",\"cs.LG\",\"cs.RO\"]","methods":"[]","has_code":false}