SuperUDF: Self-supervised UDF Estimation for Surface Reconstruction
This addresses surface reconstruction for computer graphics and vision applications, offering an incremental improvement with new regularization and prior integration.
The paper tackles surface reconstruction from 3D point clouds using unsigned distance functions (UDFs) to handle open surfaces, proposing SuperUDF with self-supervised learning and a novel regularization, resulting in outperforming state-of-the-art methods on public datasets in quality and efficiency.
Learning-based surface reconstruction based on unsigned distance functions (UDF) has many advantages such as handling open surfaces. We propose SuperUDF, a self-supervised UDF learning which exploits a learned geometry prior for efficient training and a novel regularization for robustness to sparse sampling. The core idea of SuperUDF draws inspiration from the classical surface approximation operator of locally optimal projection (LOP). The key insight is that if the UDF is estimated correctly, the 3D points should be locally projected onto the underlying surface following the gradient of the UDF. Based on that, a number of inductive biases on UDF geometry and a pre-learned geometry prior are devised to learn UDF estimation efficiently. A novel regularization loss is proposed to make SuperUDF robust to sparse sampling. Furthermore, we also contribute a learning-based mesh extraction from the estimated UDFs. Extensive evaluations demonstrate that SuperUDF outperforms the state of the arts on several public datasets in terms of both quality and efficiency. Code url is https://github.com/THHHomas/SuperUDF.