Consistency as Regularization for Unsupervised Shadow Removal

• URL: http://arxiv.org/abs/2609.01806v1
• Date: Tue, 01 Sep 2026 19:26:25 GMT
• Title: Consistency as Regularization for Unsupervised Shadow Removal
• Abstract summary: We propose ShadowCLR, an unsupervised framework that learns shadow removal directly from shadow images.<n>Our key observation is that shadows vary across observations while the underlying scene content remains largely consistent.<n>Experiments on multiple benchmarks show that ShadowCLR competitive and often superior performance over state-of-the-art unsupervised methods.
• Score: 1.2289361708127875
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Shadow removal is an important preprocessing step for many vision tasks, yet existing supervised methods require paired shadow and shadow-free images, while unsupervised approaches often still rely on shadow masks or shadow-free references. We propose ShadowCLR, an unsupervised framework that learns shadow removal directly from shadow images. Our key observation is that shadows vary across observations while the underlying scene content remains largely consistent. We therefore use consistency across shadow observations as regularization, encouraging the model to recover scene-consistent appearance while suppressing shadow-specific variations. Global and local consistency further enable us to explore visually related images, learn from imperfectly aligned observations, and focus the representation on shared scene information. Experiments on multiple benchmarks show that ShadowCLR achieves competitive and often superior performance over state-of-the-art unsupervised methods, demonstrating that consistency can provide regularization for shadow removal without shadow masks or shadow-free images.

Related papers

• Revisiting Shadow Detection from a Vision-Language Perspective [88.46763399969217]
  Shadow Vision--Language (SVL) uses language as an explicit semantic reference to disambiguate shadows from visually similar dark regions.<n>SVL applies local patch-level constraints with text embeddings to improve fine-grained discrimination under challenging appearance conditions.<n>Built on a frozen DINOv3 image encoder, the framework learns only lightweight projection and decoding modules, yielding a parameter-efficient design with less than $1%$ trainable parameters.
  arXiv  Detail & Related papers  (2026-05-12T08:42:30Z)
• MetaShadow: Object-Centered Shadow Detection, Removal, and Synthesis [64.00425120075045]
  Shadows are often under-considered or even ignored in image editing applications, limiting the realism of the edited results.<n>In this paper, we introduce MetaShadow, a three-in-one versatile framework that enables detection, removal, and controllable synthesis of shadows in natural images in an object-centered fashion.
  arXiv  Detail & Related papers  (2024-12-03T18:04:42Z)
• OmniSR: Shadow Removal under Direct and Indirect Lighting [16.90413085184936]
  A significant challenge in removing shadows from indirect illumination is obtaining shadow-free images to train the shadow removal network.<n>We propose a novel rendering pipeline for generating shadowed and shadow-free images under direct and indirect illumination.<n>We also propose an innovative shadow removal network that explicitly integrates semantic and geometric priors through concatenation and attention mechanisms.
  arXiv  Detail & Related papers  (2024-10-02T16:30:10Z)
• Shadow Removal Refinement via Material-Consistent Shadow Edges [33.8383848078524]
  On both sides of shadow edges traversing regions with the same material, the original color and textures should be the same if the shadow is removed properly. We fine-tune SAM, an image segmentation foundation model, to produce a shadow-invariant segmentation and then extract material-consistent shadow edges. We demonstrate the effectiveness of our method in improving shadow removal results on more challenging, in-the-wild images.
  arXiv  Detail & Related papers  (2024-09-10T20:16:28Z)
• Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey [78.84004293081631]
  The patterns of shadows are arbitrary, varied, and often have highly complex trace structures. The degradation caused by shadows is spatially non-uniform, resulting in inconsistencies in illumination and color between shadow and non-shadow areas. Recent developments in this field are primarily driven by deep learning-based solutions.
  arXiv  Detail & Related papers  (2024-07-11T20:58:38Z)
• Estimating Reflectance Layer from A Single Image: Integrating Reflectance Guidance and Shadow/Specular Aware Learning [66.36104525390316]
  We propose a two-stage learning method, including reflectance guidance and a Shadow/Specular-Aware (S-Aware) network to tackle the problem. In the first stage, an initial reflectance layer free from shadows and specularities is obtained with the constraint of novel losses. To further enforce the reflectance layer to be independent of shadows and specularities in the second-stage refinement, we introduce an S-Aware network that distinguishes the reflectance image from the input image.
  arXiv  Detail & Related papers  (2022-11-27T07:26:41Z)
• DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity [54.831083157152136]
  We present a method that removes hard, soft and self shadows based on adaptive attention and ViT similarity. Our method outperforms state-of-the-art methods on the SRD, AISTD, LRSS, USR and UIUC datasets.
  arXiv  Detail & Related papers  (2022-11-15T12:15:29Z)
• Shadow-Aware Dynamic Convolution for Shadow Removal [80.82708225269684]
  We introduce a novel Shadow-Aware Dynamic Convolution (SADC) module to decouple the interdependence between the shadow region and the non-shadow region. Inspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module. We develop a novel intra-convolution distillation loss to strengthen the information flow from the non-shadow region to the shadow region.
  arXiv  Detail & Related papers  (2022-05-10T14:00:48Z)
• UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal [14.898039056038789]
  We introduce a novel weakly supervised shadow removal framework UnShadowNet. It is composed of a DeShadower network responsible for the removal of the extracted shadow under the guidance of an Illumination network. We show that UnShadowNet can be easily extended to a fully-supervised set-up to exploit the ground-truth when available.
  arXiv  Detail & Related papers  (2022-03-29T11:17:02Z)
• Self-Supervised Shadow Removal [130.6657167667636]
  We propose an unsupervised single image shadow removal solution via self-supervised learning by using a conditioned mask. In contrast to existing literature, we do not require paired shadowed and shadow-free images, instead we rely on self-supervision and jointly learn deep models to remove and add shadows to images.
  arXiv  Detail & Related papers  (2020-10-22T11:33:41Z)
• Unsupervised Shadow Removal Using Target Consistency Generative Adversarial Network [3.1664163912309613]
  Unsupervised shadow removal aims to learn a non-linear function to map the original image from shadow domain to non-shadow domain in the absence of paired shadow and non-shadow data. We develop a simple yet efficient target-consistency generative adversarial network (TC-GAN) for the shadow removal task in the unsupervised manner.
  arXiv  Detail & Related papers  (2020-10-03T06:55:26Z)

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.