# No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry

arXiv: https://arxiv.org/abs/2012.10565 · HTML: https://mlsanity.com/paper/2012.10565/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2020.

## Built on by (most cited first, 9 of 9)

- [Latent Feature-Guided Diffusion Models for Shadow Removal](https://mlsanity.com/paper/2312.02156/) (2023)
- [S3R-Net: A Single-Stage Approach to Self-Supervised Shadow Removal](https://mlsanity.com/paper/2404.12103/) (2024)
- [Virtual Home Staging: Inverse Rendering and Editing an Indoor Panorama under Natural Illumination](https://mlsanity.com/paper/2311.12265/) (2023)
- [MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis](https://mlsanity.com/paper/2412.02635/) (2024)
- [An Empty Room is All We Want: Automatic Defurnishing of Indoor Panoramas](https://mlsanity.com/paper/2405.03682/) (2024)
- [Layout Aware Inpainting for Automated Furniture Removal in Indoor Scenes](https://mlsanity.com/paper/2210.15796/) (2022)
- [Semantic UV mapping to improve texture inpainting for indoor scenes](https://mlsanity.com/paper/2407.09248/) (2024)
- [CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement](https://mlsanity.com/paper/2604.18032/) (2026)
- [WildShadowRemover: In-the-Wild Video Shadow Removal via Detail-Preserving Video Diffusion Models](https://mlsanity.com/paper/2607.26203/) (2026)

## Abstract (arXiv)

Removing objects from images is a challenging problem that is important for many applications, including mixed reality. For believable results, the shadows that the object casts should also be removed. Current inpainting-based methods only remove the object itself, leaving shadows behind, or at best require specifying shadow regions to inpaint. We introduce a deep learning pipeline for removing a shadow along with its caster. We leverage rough scene models in order to remove a wide variety of shadows (hard or soft, dark or subtle, large or thin) from surfaces with a wide variety of textures. We train our pipeline on synthetically rendered data, and show qualitative and quantitative results on both synthetic and real scenes.