GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splatting

CVPR 2025

Shujuan Li1, Yu-Shen Liu1, Zhizhong Han2,
1Tsinghua University, 2Wayne State University
Paper Code

Abstract

Reconstructing open surfaces from multi-view images is vital in digitalizing complex objects in daily life. A widely used strategy is to learn unsigned distance functions (UDFs) by checking if their appearance conforms to the image observations through neural rendering. However, it is still hard to learn the continuous and implicit UDF representations through 3D Gaussians splatting (3DGS) due to the discrete and explicit scene representations, i.e., 3D Gaussians. To resolve this issue, we propose a novel approach to bridge the gap between 3D Gaussians and UDFs. Our key idea is to overfit thin and flat 2D Gaussian planes on surfaces, and then, leverage the self-supervision and gradient-based inference to supervise unsigned distances in both near and far area to surfaces. To this end, we introduce novel constraints and strategies to constrain the learning of 2D Gaussians to pursue more stable optimization and more reliable self-supervision, addressing the challenges brought by complicated gradient field on or near the zero level set of UDFs. We report numerical and visual comparisons with the state-of-the-art on widely used benchmarks and real data to show our advantages in terms of accuracy, efficiency, completeness, and sharpness of reconstructed open surfaces with boundaries.

Method

Overview

Overview of our method. We introduce a novel framework that can estimate unsigned distances along with the learning of 3D Gaussians in a fully differentiable way, which leverages the characters of 3D Gaussians to stabilize the gradients near the zero level set and mine self-supervision adaptively. The UDF is optimized with the rendering process. To ensure Gaussians provide more accurate clues of the surfaces, the Gaussians are projected to the zero level set of the UDF. Projecting random queries to the Gaussian centers helps the UDF learn coarse shapes in far area and unsigned distances recovered near the Gaussian plane compensates for the sparsity of Gaussian centers.

Comparison Results

BibTeX

@inproceedings{li2025gaussianudf,
      title={GaussianUDF: Inferring Unsigned Distance Functions through 3D Gaussian Splatting},
      author={Li, Shujuan and Liu, Yu-Shen and Han, Zhizhong},
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
      year={2025}
    }