# DeepShadow: Neural Shape from Shadow

arXiv: https://arxiv.org/abs/2203.15065 · HTML: https://mlsanity.com/paper/2203.15065/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 34 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 18 of 18)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis](https://mlsanity.com/paper/2012.03927/) (2020)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [NeRFactor: Neural Factorization of Shape and Reflectance Under an Unknown Illumination](https://mlsanity.com/paper/2106.01970/) (2021)
- [PS-FCN: A Flexible Learning Framework for Photometric Stereo](https://mlsanity.com/paper/1807.08696/) (2018)
- [Self-calibrating Deep Photometric Stereo Networks](https://mlsanity.com/paper/1903.07366/) (2019)
- [Neural Inverse Rendering for General Reflectance Photometric Stereo](https://mlsanity.com/paper/1802.10328/) (2018)
- [Uncalibrated Neural Inverse Rendering for Photometric Stereo of General Surfaces](https://mlsanity.com/paper/2012.06777/) (2020)
- [Deep Photometric Stereo for Non-Lambertian Surfaces](https://mlsanity.com/paper/2007.13145/) (2020)
- [PX-NET: Simple and Efficient Pixel-Wise Training of Photometric Stereo Networks](https://mlsanity.com/paper/2008.04933/) (2020)
- [Efficient and Differentiable Shadow Computation for Inverse Problems](https://mlsanity.com/paper/2104.00359/) (2021)
- [A CNN Based Approach for the Near-Field Photometric Stereo Problem](https://mlsanity.com/paper/2009.05792/) (2020)
- [Photometric Depth Super-Resolution](https://mlsanity.com/paper/1809.10097/) (2018)
- [Self-supervised Learning for Single View Depth and Surface Normal Estimation](https://mlsanity.com/paper/1903.00112/) (2019)
- [Depth Super-Resolution Meets Uncalibrated Photometric Stereo](https://mlsanity.com/paper/1708.00411/) (2017)

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

- [S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint](https://mlsanity.com/paper/2210.08936/) (2022)
- [ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision](https://mlsanity.com/paper/2211.14086/) (2022)
- [PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar](https://mlsanity.com/paper/2312.14239/) (2023)
- [DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering](https://mlsanity.com/paper/2303.15101/) (2023)
- [Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting](https://mlsanity.com/paper/2410.07266/) (2024)
- [Soft Shadow Diffusion (SSD): Physics-inspired Learning for 3D Computational Periscopy](https://mlsanity.com/paper/2601.12257/) (2026)

## Abstract (arXiv)

This paper presents DeepShadow, a one-shot method for recovering the depth map and surface normals from photometric stereo shadow maps. Previous works that try to recover the surface normals from photometric stereo images treat cast shadows as a disturbance. We show that the self and cast shadows not only do not disturb 3D reconstruction, but can be used alone, as a strong learning signal, to recover the depth map and surface normals. We demonstrate that 3D reconstruction from shadows can even outperform shape-from-shading in certain cases. To the best of our knowledge, our method is the first to reconstruct 3D shape-from-shadows using neural networks. The method does not require any pre-training or expensive labeled data, and is optimized during inference time.