# LightSAL: Lightweight Sign Agnostic Learning for Implicit Surface Representation

arXiv: https://arxiv.org/abs/2103.14273 · HTML: https://mlsanity.com/paper/2103.14273/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 61 references that are in the map.
- First posted on arXiv 26 Mar 2021.

## Builds on (most cited first, 30 of 43)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [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)
- [Deep Sets](https://mlsanity.com/paper/1703.06114/) (2017)
- [Learning Implicit Fields for Generative Shape Modeling](https://mlsanity.com/paper/1812.02822/) (2018)
- [Geometric deep learning: going beyond Euclidean data](https://mlsanity.com/paper/1611.08097/) (2016)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images](https://mlsanity.com/paper/1804.01654/) (2018)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generation](https://mlsanity.com/paper/1802.05384/) (2018)
- [PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows](https://mlsanity.com/paper/1906.12320/) (2019)
- [SAL: Sign Agnostic Learning of Shapes from Raw Data](https://mlsanity.com/paper/1911.10414/) (2019)
- [Local Implicit Grid Representations for 3D Scenes](https://mlsanity.com/paper/2003.08981/) (2020)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [Generating 3D faces using Convolutional Mesh Autoencoders](https://mlsanity.com/paper/1807.10267/) (2018)
- [Neural Unsigned Distance Fields for Implicit Function Learning](https://mlsanity.com/paper/2010.13938/) (2020)
- [Shape Completion using 3D-Encoder-Predictor CNNs and Shape Synthesis](https://mlsanity.com/paper/1612.00101/) (2016)
- [Texture Fields: Learning Texture Representations in Function Space](https://mlsanity.com/paper/1905.07259/) (2019)
- [Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs](https://mlsanity.com/paper/1703.09438/) (2017)
- [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019)
- [Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency](https://mlsanity.com/paper/1704.06254/) (2017)
- [NASA: Neural Articulated Shape Approximation](https://mlsanity.com/paper/1912.03207/) (2019)
- [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018)

## Built on by (most cited first, 7 of 7)

- [Beyond Periodicity: Towards a Unifying Framework for Activations in Coordinate-MLPs](https://mlsanity.com/paper/2111.15135/) (2021)
- [Surface Reconstruction from Point Clouds: A Survey and a Benchmark](https://mlsanity.com/paper/2205.02413/) (2022)
- [Learning Positional Embeddings for Coordinate-MLPs](https://mlsanity.com/paper/2112.11577/) (2021)
- [On Regularizing Coordinate-MLPs](https://mlsanity.com/paper/2202.00790/) (2022)
- [How You Start Matters for Generalization](https://mlsanity.com/paper/2206.08558/) (2022)
- [Optimizing Implicit Neural Representations from Point Clouds via Energy-Based Models](https://mlsanity.com/paper/2311.02601/) (2023)
- [Convolutional Neural Network-based Efficient Dense Point Cloud Generation using Unsigned Distance Fields](https://mlsanity.com/paper/2203.11537/) (2022)

## Abstract (arXiv)

Recently, several works have addressed modeling of 3D shapes using deep neural networks to learn implicit surface representations. Up to now, the majority of works have concentrated on reconstruction quality, paying little or no attention to model size or training time. This work proposes LightSAL, a novel deep convolutional architecture for learning 3D shapes; the proposed work concentrates on efficiency both in network training time and resulting model size. We build on the recent concept of Sign Agnostic Learning for training the proposed network, relying on signed distance fields, with unsigned distance as ground truth. In the experimental section of the paper, we demonstrate that the proposed architecture outperforms previous work in model size and number of required training iterations, while achieving equivalent accuracy. Experiments are based on the D-Faust dataset that contains 41k 3D scans of human shapes. The proposed model has been implemented in PyTorch.