# CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement

arXiv: https://arxiv.org/abs/2604.18032 · HTML: https://mlsanity.com/paper/2604.18032/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 49 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Focal Frequency Loss for Image Reconstruction and Synthesis](https://mlsanity.com/paper/2012.12821/) (2020)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN](https://mlsanity.com/paper/1911.08718/) (2019)
- [ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal](https://mlsanity.com/paper/2212.04711/) (2022)
- [Shadow Removal via Shadow Image Decomposition](https://mlsanity.com/paper/1908.08628/) (2019)
- [Mask-ShadowGAN: Learning to Remove Shadows from Unpaired Data](https://mlsanity.com/paper/1903.10683/) (2019)
- [Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Models](https://mlsanity.com/paper/2304.08291/) (2023)
- [Auto-Exposure Fusion for Single-Image Shadow Removal](https://mlsanity.com/paper/2103.01255/) (2021)
- [DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network](https://mlsanity.com/paper/2207.10434/) (2022)
- [From Shadow Segmentation to Shadow Removal](https://mlsanity.com/paper/2008.00267/) (2020)
- [From Shadow Generation to Shadow Removal](https://mlsanity.com/paper/2103.12997/) (2021)
- [Physics-based Shadow Image Decomposition for Shadow Removal](https://mlsanity.com/paper/2012.13018/) (2020)
- [ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer](https://mlsanity.com/paper/2406.02559/) (2024)
- [SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes](https://mlsanity.com/paper/2310.13030/) (2023)
- [OmniSR: Shadow Removal under Direct and Indirect Lighting](https://mlsanity.com/paper/2410.01719/) (2024)
- [LIRM: Large Inverse Rendering Model for Progressive Reconstruction of Shape, Materials and View-dependent Radiance Fields](https://mlsanity.com/paper/2504.20026/) (2025)
- [Detail-Preserving Latent Diffusion for Stable Shadow Removal](https://mlsanity.com/paper/2412.17630/) (2024)
- [DiffusionLight-Turbo: Accelerated Light Probes for Free via Single-Pass Chrome Ball Inpainting](https://mlsanity.com/paper/2507.01305/) (2025)
- [No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry](https://mlsanity.com/paper/2012.10565/) (2020)
- [DenseSR: Image Shadow Removal as Dense Prediction](https://mlsanity.com/paper/2507.16472/) (2025)
- [Retinex-guided Histogram Transformer for Mask-free Shadow Removal](https://mlsanity.com/paper/2504.14092/) (2025)
- [After the Party: Navigating the Mapping From Color to Ambient Lighting](https://mlsanity.com/paper/2508.02168/) (2025)
- [PhaSR: Generalized Image Shadow Removal with Physically Aligned Priors](https://mlsanity.com/paper/2601.17470/) (2026)
- [SDE-DET: A Precision Network for Shatian Pomelo Detection in Complex Orchard Environments](https://mlsanity.com/paper/2509.19990/) (2025)
- [A Multi-Strategy Framework for Enhancing Shatian Pomelo Detection in Real-World Orchards](https://mlsanity.com/paper/2510.09948/) (2025)

## Abstract (arXiv)

Traditional shadow removal networks often treat image restoration as an unconstrained mapping, lacking the physical interpretability required to balance localized texture recovery with global illumination consistency. To address this, we propose CFSR, a multi-modal prior-driven framework that reframes shadow removal as a physics-constrained restoration process. By seamlessly integrating 3D geometric cues with large-scale foundation model semantics, CFSR effectively bridges the 2D-3D domain gap. Specifically, we first map observations into a custom HVI color space to suppress shadow-induced noise and robustly fuse RGB data with estimated depth priors. At its core, our Geometric & Semantic Dual Explicit Guided Attention mechanism utilizes DINO features and 3D surface normals to directly modulate the attention affinity matrix, structurally enforcing physical lighting constraints. To recover severely degraded regions, we inject holistic priors via a frozen CLIP encoder. Finally, our Frequency Collaborative Reconstruction Module (FCRM) achieves an optimal synthesis by decoupling the decoding process. Conditioned on geometric priors, FCRM seamlessly harmonizes the reconstruction of sharp high-frequency occlusion boundaries with the restoration of low-frequency global illumination. Extensive experiments demonstrate that CFSR achieves state-of-the-art performance across multiple challenging benchmarks.