# SuperUDF: Self-supervised UDF Estimation for Surface Reconstruction

arXiv: https://arxiv.org/abs/2308.14371 · HTML: https://mlsanity.com/paper/2308.14371/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 28 Aug 2023.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019)
- [Neural Unsigned Distance Fields for Implicit Function Learning](https://mlsanity.com/paper/2010.13938/) (2020)
- [BSP-Net: Generating Compact Meshes via Binary Space Partitioning](https://mlsanity.com/paper/1911.06971/) (2019)
- [Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces](https://mlsanity.com/paper/2011.13495/) (2020)
- [SALD: Sign Agnostic Learning with Derivatives](https://mlsanity.com/paper/2006.05400/) (2020)
- [POCO: Point Convolution for Surface Reconstruction](https://mlsanity.com/paper/2201.01831/) (2022)
- [MeshUDF: Fast and Differentiable Meshing of Unsigned Distance Field Networks](https://mlsanity.com/paper/2111.14549/) (2021)
- [Deep Implicit Moving Least-Squares Functions for 3D Reconstruction](https://mlsanity.com/paper/2103.12266/) (2021)
- [Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors](https://mlsanity.com/paper/2204.10603/) (2022)
- [GIFS: Neural Implicit Function for General Shape Representation](https://mlsanity.com/paper/2204.07126/) (2022)
- [Deep Implicit Surface Point Prediction Networks](https://mlsanity.com/paper/2106.05779/) (2021)
- [Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction](https://mlsanity.com/paper/2108.08478/) (2021)
- [SSRNet: Scalable 3D Surface Reconstruction Network](https://mlsanity.com/paper/1911.07401/) (2019)
- [DUDE: Deep Unsigned Distance Embeddings for Hi-Fidelity Representation of Complex 3D Surfaces](https://mlsanity.com/paper/2011.02570/) (2020)

## Built on by (most cited first, 6 of 6)

- [SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies](https://mlsanity.com/paper/2508.00366/) (2025)
- [3D Shape Completion on Unseen Categories:A Weakly-supervised Approach](https://mlsanity.com/paper/2401.10578/) (2024)
- [PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction](https://mlsanity.com/paper/2310.07997/) (2023)
- [Surface Reconstruction from Point Clouds via Grid-based Intersection Prediction](https://mlsanity.com/paper/2403.14085/) (2024)
- [Polyhedral Surface: Self-supervised Point Cloud Reconstruction Based on Polyhedral Surface](https://mlsanity.com/paper/2310.14560/) (2023)
- [VoxNeuS: Enhancing Voxel-Based Neural Surface Reconstruction via Gradient Interpolation](https://mlsanity.com/paper/2406.07170/) (2024)

## Abstract (arXiv)

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.