While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and DCUDF for extracting the local minimal average distance surface. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces. Our source code is atthis https URL.
View on arXiv@article{xu2025_2406.00346, title={ Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction }, author={ Cheng Xu and Fei Hou and Wencheng Wang and Hong Qin and Zhebin Zhang and Ying He }, journal={arXiv preprint arXiv:2406.00346}, year={ 2025 } }