# Enhancing Surface Neural Implicits with Curvature-Guided Sampling and Uncertainty-Augmented Representations

arXiv: https://arxiv.org/abs/2306.02099 · HTML: https://mlsanity.com/paper/2306.02099/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 3 Jun 2023.

## Builds on (most cited first, 25 of 25)

- [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)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Volume Rendering of Neural Implicit Surfaces](https://mlsanity.com/paper/2106.12052/) (2021)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [Neural Unsigned Distance Fields for Implicit Function Learning](https://mlsanity.com/paper/2010.13938/) (2020)
- [Shape As Points: A Differentiable Poisson Solver](https://mlsanity.com/paper/2106.03452/) (2021)
- [Neural-Pull: Learning Signed Distance Functions from Point Clouds by Learning to Pull Space onto Surfaces](https://mlsanity.com/paper/2011.13495/) (2020)
- [NeuroMorph: Unsupervised Shape Interpolation and Correspondence in One Go](https://mlsanity.com/paper/2106.09431/) (2021)
- [A Large Dataset of Object Scans](https://mlsanity.com/paper/1602.02481/) (2016)
- [Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priors](https://mlsanity.com/paper/2204.10603/) (2022)
- [LIMP: Learning Latent Shape Representations with Metric Preservation Priors](https://mlsanity.com/paper/2003.12283/) (2020)
- [Deep Level Sets: Implicit Surface Representations for 3D Shape Inference](https://mlsanity.com/paper/1901.06802/) (2019)
- [RoutedFusion: Learning Real-time Depth Map Fusion](https://mlsanity.com/paper/2001.04388/) (2020)
- [Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning](https://mlsanity.com/paper/1904.02113/) (2019)
- [Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Clouds](https://mlsanity.com/paper/2203.14048/) (2022)
- [Exploring Differential Geometry in Neural Implicits](https://mlsanity.com/paper/2201.09263/) (2022)
- [Augmenting Implicit Neural Shape Representations with Explicit Deformation Fields](https://mlsanity.com/paper/2108.08931/) (2021)
- [Local Deep Implicit Functions for 3D Shape](https://mlsanity.com/paper/1912.06126/) (2019)
- [Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction](https://mlsanity.com/paper/2111.13652/) (2021)
- [High-Quality RGB-D Reconstruction via Multi-View Uncalibrated Photometric Stereo and Gradient-SDF](https://mlsanity.com/paper/2210.12202/) (2022)
- [Unsigned Distance Field as an Accurate 3D Scene Representation for Neural Scene Completion](https://mlsanity.com/paper/2203.09167/) (2022)

## Built on by (most cited first, 2 of 2)

- [Geometric implicit neural representations for signed distance functions](https://mlsanity.com/paper/2511.07206/) (2025)
- [FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models](https://mlsanity.com/paper/2506.16627/) (2025)

## Abstract (arXiv)

Neural implicit representations have become a popular choice for modeling surfaces due to their adaptability in resolution and support for complex topology. While previous works have achieved impressive reconstruction quality by training on ground truth point clouds or meshes, they often do not discuss the data acquisition and ignore the effect of input quality and sampling methods during reconstruction. In this paper, we introduce a method that directly digests depth images for the task of high-fidelity 3D reconstruction. To this end, a simple sampling strategy is proposed to generate highly effective training data, by incorporating differentiable geometric features computed directly based on the input depth images with only marginal computational cost. Due to its simplicity, our sampling strategy can be easily incorporated into diverse popular methods, allowing their training process to be more stable and efficient. Despite its simplicity, our method outperforms a range of both classical and learning-based baselines and demonstrates state-of-the-art results in both synthetic and real-world datasets.