SOTAVerified

Image Shadow Removal

Merge with the Shadow Removal

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–25 of 38 papers

TitleStatusHype
Single-Image Shadow Removal Using Deep Learning: A Comprehensive SurveyCode3
ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier TransformerCode2
Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion ModelsCode2
DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided NetworkCode2
High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing NetCode2
A Decoupled Multi-Task Network for Shadow RemovalCode1
A Shadow Imaging Bilinear Model and Three-branch Residual Network for Shadow RemovalCode1
Auto-Exposure Fusion for Single-Image Shadow RemovalCode1
BEDSR-Net: A Deep Shadow Removal Network From a Single Document ImageCode1
Document Image Shadow Removal Guided by Color-Aware BackgroundCode1
HomoFormer: Homogenized Transformer for Image Shadow RemovalCode1
Leveraging Inpainting for Single-Image Shadow RemovalCode1
OmniSR: Shadow Removal under Direct and Indirect LightingCode1
ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow RemovalCode1
DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT SimilarityCode1
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow RemovalCode1
ShadowFormer: Global Context Helps Image Shadow RemovalCode1
Appearance Harmonization for Single Image Shadow Removal—0
Variational Degeneration to Structural Refinement: A Unified Framework for Superimposed Image Decomposition—0
ShadowMamba: State-Space Model with Boundary-Region Selective Scan for Shadow Removal—0
Deshadow-Anything: When Segment Anything Model Meets Zero-shot shadow removal—0
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks—0
Deep Adversarial Decomposition: A Unified Framework for Separating Superimposed Images—0
Image Shadow Removal Using End-to-End Deep Convolutional Neural Networks—0
Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal—0
Show:102550
← PrevPage 1 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OmniSRAverage PSNR (dB)30.38—Unverified