# Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction

arXiv: https://arxiv.org/abs/2003.10983 · HTML: https://mlsanity.com/paper/2003.10983/

## Key facts

- Cited by 321 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Mar 2020.

## Built on by (most cited first, 30 of 321)

- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [NICE-SLAM: Neural Implicit Scalable Encoding for SLAM](https://mlsanity.com/paper/2112.12130/) (2021)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [iMAP: Implicit Mapping and Positioning in Real-Time](https://mlsanity.com/paper/2103.12352/) (2021)
- [3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models](https://mlsanity.com/paper/2301.11445/) (2023)
- [Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes](https://mlsanity.com/paper/2101.10994/) (2021)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Advances in Neural Rendering](https://mlsanity.com/paper/2111.05849/) (2021)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)
- [StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation](https://mlsanity.com/paper/2112.11427/) (2021)
- [Mixture of Volumetric Primitives for Efficient Neural Rendering](https://mlsanity.com/paper/2103.01954/) (2021)
- [3D Neural Field Generation using Triplane Diffusion](https://mlsanity.com/paper/2211.16677/) (2022)
- [NeRV: Neural Representations for Videos](https://mlsanity.com/paper/2110.13903/) (2021)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [A Survey on 3D Gaussian Splatting](https://mlsanity.com/paper/2401.03890/) (2024)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation](https://mlsanity.com/paper/2112.08867/) (2021)
- [Shape As Points: A Differentiable Poisson Solver](https://mlsanity.com/paper/2106.03452/) (2021)
- [NEAT: Neural Attention Fields for End-to-End Autonomous Driving](https://mlsanity.com/paper/2109.04456/) (2021)
- [HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion](https://mlsanity.com/paper/2303.17015/) (2023)
- [BACON: Band-limited Coordinate Networks for Multiscale Scene Representation](https://mlsanity.com/paper/2112.04645/) (2021)
- [Modulated Periodic Activations for Generalizable Local Functional Representations](https://mlsanity.com/paper/2104.03960/) (2021)
- [Diffusion-SDF: Text-to-Shape via Voxelized Diffusion](https://mlsanity.com/paper/2212.03293/) (2022)
- [NeSF: Neural Semantic Fields for Generalizable Semantic Segmentation of 3D Scenes](https://mlsanity.com/paper/2111.13260/) (2021)
- [latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction](https://mlsanity.com/paper/2403.16292/) (2024)
- [Light Field Neural Rendering](https://mlsanity.com/paper/2112.09687/) (2021)
- [LEAP: Learning Articulated Occupancy of People](https://mlsanity.com/paper/2104.06849/) (2021)

## Abstract (arXiv)

Efficiently reconstructing complex and intricate surfaces at scale is a long-standing goal in machine perception. To address this problem we introduce Deep Local Shapes (DeepLS), a deep shape representation that enables encoding and reconstruction of high-quality 3D shapes without prohibitive memory requirements. DeepLS replaces the dense volumetric signed distance function (SDF) representation used in traditional surface reconstruction systems with a set of locally learned continuous SDFs defined by a neural network, inspired by recent work such as DeepSDF. Unlike DeepSDF, which represents an object-level SDF with a neural network and a single latent code, we store a grid of independent latent codes, each responsible for storing information about surfaces in a small local neighborhood. This decomposition of scenes into local shapes simplifies the prior distribution that the network must learn, and also enables efficient inference. We demonstrate the effectiveness and generalization power of DeepLS by showing object shape encoding and reconstructions of full scenes, where DeepLS delivers high compression, accuracy, and local shape completion.