# Shape Reconstruction by Learning Differentiable Surface Representations

arXiv: https://arxiv.org/abs/1911.11227 · HTML: https://mlsanity.com/paper/1911.11227/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Nov 2019.

## Built on by (most cited first, 30 of 37)

- [The Power of Points for Modeling Humans in Clothing](https://mlsanity.com/paper/2109.01137/) (2021)
- [SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements](https://mlsanity.com/paper/2104.07660/) (2021)
- [Surface Reconstruction from Point Clouds by Learning Predictive Context Priors](https://mlsanity.com/paper/2204.11015/) (2022)
- [Learning Implicit Templates for Point-Based Clothed Human Modeling](https://mlsanity.com/paper/2207.06955/) (2022)
- [Neural Surface Maps](https://mlsanity.com/paper/2103.16942/) (2021)
- [An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion](https://mlsanity.com/paper/2408.03178/) (2024)
- [GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation](https://mlsanity.com/paper/2211.16762/) (2022)
- [Neural Jacobian Fields: Learning Intrinsic Mappings of Arbitrary Meshes](https://mlsanity.com/paper/2205.02904/) (2022)
- [Unsupervised Learning of Fine Structure Generation for 3D Point Clouds by 2D Projection Matching](https://mlsanity.com/paper/2108.03746/) (2021)
- [CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition](https://mlsanity.com/paper/2304.03167/) (2023)
- [NeuForm: Adaptive Overfitting for Neural Shape Editing](https://mlsanity.com/paper/2207.08890/) (2022)
- [Neural Vector Fields: Implicit Representation by Explicit Learning](https://mlsanity.com/paper/2303.04341/) (2023)
- [Flatten Anything: Unsupervised Neural Surface Parameterization](https://mlsanity.com/paper/2405.14633/) (2024)
- [Neural Geometry Processing via Spherical Neural Surfaces](https://mlsanity.com/paper/2407.07755/) (2024)
- [Explicit Neural Surfaces: Learning Continuous Geometry With Deformation Fields](https://mlsanity.com/paper/2306.02956/) (2023)
- [Neural Convolutional Surfaces](https://mlsanity.com/paper/2204.02289/) (2022)
- [GAPS: Geometry-Aware, Physics-Based, Self-Supervised Neural Garment Draping](https://mlsanity.com/paper/2312.01490/) (2023)
- [Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases](https://mlsanity.com/paper/2104.06950/) (2021)
- [WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation](https://mlsanity.com/paper/2203.12917/) (2022)
- [Garment Avatars: Realistic Cloth Driving using Pattern Registration](https://mlsanity.com/paper/2206.03373/) (2022)
- [Minimal Neural Atlas: Parameterizing Complex Surfaces with Minimal Charts and Distortion](https://mlsanity.com/paper/2207.14782/) (2022)
- [Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering](https://mlsanity.com/paper/2310.05524/) (2023)
- [FlexPara: Flexible Neural Surface Parameterization](https://mlsanity.com/paper/2504.19210/) (2025)
- [Modeling 3D Surface Manifolds with a Locally Conditioned Atlas](https://mlsanity.com/paper/2102.05984/) (2021)
- [TutteNet: Injective 3D Deformations by Composition of 2D Mesh Deformations](https://mlsanity.com/paper/2406.12121/) (2024)
- [Learning Local Pattern Modularization for Point Cloud Reconstruction from Unseen Classes](https://mlsanity.com/paper/2408.14279/) (2024)
- [Spatially-Adaptive Hash Encodings For Neural Surface Reconstruction](https://mlsanity.com/paper/2412.05179/) (2024)
- [Learning Joint Surface Atlases](https://mlsanity.com/paper/2206.06273/) (2022)
- [Deformable Surface Reconstruction via Riemannian Metric Preservation](https://mlsanity.com/paper/2212.11596/) (2022)
- [Neural Vector Fields: Generalizing Distance Vector Fields by Codebooks and Zero-Curl Regularization](https://mlsanity.com/paper/2309.01512/) (2023)

## Abstract (arXiv)

Generative models that produce point clouds have emerged as a powerful tool to represent 3D surfaces, and the best current ones rely on learning an ensemble of parametric representations. Unfortunately, they offer no control over the deformations of the surface patches that form the ensemble and thus fail to prevent them from either overlapping or collapsing into single points or lines. As a consequence, computing shape properties such as surface normals and curvatures becomes difficult and unreliable. In this paper, we show that we can exploit the inherent differentiability of deep networks to leverage differential surface properties during training so as to prevent patch collapse and strongly reduce patch overlap. Furthermore, this lets us reliably compute quantities such as surface normals and curvatures. We will demonstrate on several tasks that this yields more accurate surface reconstructions than the state-of-the-art methods in terms of normals estimation and amount of collapsed and overlapped patches.