CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement

• URL: http://arxiv.org/abs/2604.18032v1
• Date: Mon, 20 Apr 2026 09:58:17 GMT
• Title: CFSR: Geometry-Conditioned Shadow Removal via Physical Disentanglement
• Abstract summary: CFSR is a multi-modal prior-driven framework that reframes shadow removal as a physics-constrained restoration process.<n> CFSR achieves state-of-the-art performance across multiple challenging benchmarks.
• Score: 22.031783191814323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction [3.7567584936415166]
  Sparse-view computed tomography (CT) reduces radiation dose by acquiring fewer projection views, but the resulting inverse problem is highly ill-posed.<n>Existing deep reconstruction methods have achieved promising performance, yet many rely on first-order updates or large regularization networks.<n>We propose textbfCG-GLORE, a compact deep unrolling framework inspired by second-order optimization for sparse-view CT reconstruction.
  arXiv  Detail & Related papers  (2026-08-15T14:08:44Z)
• PRISM3D: Probabilistic Refinement and Robust Initialization for Physically Consistent Scene Modeling under Extreme Motion Blur [9.855875137621622]
  We address the inverse problem of blind 3D scene reconstruction from extremely motion-red images.<n>Existing approaches typically circumvent this bottleneck by relying on impractical sharp-image supervision.<n>We introduce PRISM3D, a unified framework enabling robust reconstruction directly from severely degraded inputs.
  arXiv  Detail & Related papers  (2026-07-04T12:45:11Z)
• GARDEN: Gravity-Aligned Reconstruction of Disentangled ENvironments from RGB images [61.2170105836525]
  We propose an RGB-only framework that reformulates reconstruction as physically-grounded scene factorization and outputs a structured hybrid scene representation.<n>The resulting representation combines explicit rigid bodies with a decoupled background, enabling direct physics simulation while preserving visual realism.
  arXiv  Detail & Related papers  (2026-06-02T17:13:01Z)
• HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation [50.46910397782266]
  Hyperspectral image (HSI) restoration is crucial for reliable analysis, as real HSIs suffer from degradations like noise, blur, and resolution loss.<n>We present HIR-ALIGN, a plug-and-play target-adaptive augmentation framework that enhances hyperspectral image restoration by augmenting limited training images with synthetic data that closely matches the target distribution using no extra data.
  arXiv  Detail & Related papers  (2026-05-13T14:14:13Z)
• Naka-GS: A Bionics-inspired Dual-Branch Naka Correction and Progressive Point Pruning for Low-Light 3DGS [5.922483935990404]
  We present NAKA-GS, a bionics-inspired framework for low-light 3D Gaussian Splatting.<n>Our method combines physics-prior low-light enhancement, dual-branch input modeling, frequency-decoupled correction, and mask-guided optimization.<n>The proposed method was presented in the NTIRE 3D Restoration and Reconstruction (3DRR) Challenge, and outperformed the baseline methods by a large margin.
  arXiv  Detail & Related papers  (2026-04-13T07:58:58Z)
• R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting [59.29134814041703]
  Physical adversarial camouflage poses a severe security threat to autonomous driving systems.<n>Current methods fail to generalize across diverse geometric (e.g., viewing configurations) and radiometric variations.<n>We propose the Relightable Physical 3D Gaussian Splatting framework (R-PGA)
  arXiv  Detail & Related papers  (2026-03-27T04:38:04Z)
• PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [76.9760302941819]
  PolGS++ is a polarimetric Gaussian Splatting framework for fast reflective surface reconstruction.<n>We introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints.
  arXiv  Detail & Related papers  (2026-03-11T14:11:42Z)
• STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction [18.777422532112105]
  Existing methods based on 3D Gaussian Splatting typically bind Gaussians to mesh triangles and model deformations solely via Linear Blend Skinning.<n>We propose STAvatar, which consists of two key components: (1) a UV-Temporal Soft Binding framework that leverages both image-based and geometric priors to learn per-Gaussian feature offsets within the UV space.<n> STAvatar achieves state-of-the-art reconstruction performance, especially in capturing fine-grained details and reconstructing frequently occluded regions.
  arXiv  Detail & Related papers  (2025-11-25T02:35:00Z)
• HBSplat: Robust Sparse-View Gaussian Reconstruction with Hybrid-Loss Guided Depth and Bidirectional Warping [11.035994094874141]
  HBSplat is a framework that seamlessly integrates robust structural cues, virtual view constraints, and occluded region completion.<n> HBSplat sets a new state-of-the-art, achieving up to 21.13 dB PSNR and 0.189 LPIPS, while maintaining real-time inference.
  arXiv  Detail & Related papers  (2025-09-29T15:03:31Z)
• HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity [8.74691272469226]
  HiNeuS is a unified framework that holistically addresses three core limitations in existing approaches.<n>We introduce: 1) Differential visibility verification through SDF-guided ray tracing; 2) Planar-conformal regularization via ray-aligned geometry patches; and 3) Physically-grounded Eikonal relaxation that dynamically modulates geometric constraints based on local gradients.
  arXiv  Detail & Related papers  (2025-06-30T13:45:25Z)
• CryoFastAR: Fast Cryo-EM Ab Initio Reconstruction Made Easy [58.86576215228903]
  We introduce CryoFastAR, the first geometric foundation model that can directly predict poses from Cryo-EM noisy images for Fast ab initio Reconstruction.<n>By integrating multi-view features and training on large-scale simulated cryo-EM data with realistic noise and CTF modulations, CryoFastAR enhances pose estimation accuracy and generalization.
  arXiv  Detail & Related papers  (2025-06-06T08:32:32Z)
• Decompositional Neural Scene Reconstruction with Generative Diffusion Prior [64.71091831762214]
  Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture, is intriguing for downstream applications.<n>Recent approaches incorporate semantic or geometric regularization to address this issue, but they suffer significant degradation in underconstrained areas.<n>We propose DP-Recon, which employs diffusion priors in the form of Score Distillation Sampling (SDS) to optimize the neural representation of each individual object under novel views.
  arXiv  Detail & Related papers  (2025-03-19T02:11:31Z)
• PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields [49.6405458373509]
  We present an inverse rendering (IR) model capable of jointly estimating scene geometry, materials, and illumination.<n>Our method is easily adaptable to other inverse rendering and 3D reconstruction frameworks that require material estimation.
  arXiv  Detail & Related papers  (2024-12-12T19:00:21Z)
• FCDM: A Physics-Guided Bidirectional Frequency Aware Convolution and Diffusion-Based Model for Sinogram Inpainting [14.043383277622874]
  Full-view sinograms require high radiation dose and long scan times.<n>Sparse-view CT alleviates this burden but yields incomplete sinograms with structured signal loss.<n>We proposemodelname, a diffusion-based framework tailored for sinograms.
  arXiv  Detail & Related papers  (2024-08-26T12:31:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.