NTIRE 2025 Image Shadow Removal Challenge Report

2025/06/18 by Florin-Alexandru Vasluianu, Vasluianu, Florin-Alexandru, Tim Seizinger +155 · 1 citation
Engineering · Physics and Astronomy · #Advanced Optical Sensing Technologies #Advanced X-ray and CT Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Laser-induced spectroscopy and plasma

paper · pdf · doi:10.48550/arxiv.2506.15524

openalex publication_date 2025/06/18 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

This work examines the findings of the NTIRE 2025 Shadow Removal Challenge. A total of 306 participants have registered, with 17 teams successfully submitting their solutions during the final evaluation phase. Following the last two editions, this challenge had two evaluation tracks: one focusing on reconstruction fidelity and the other on visual perception through a user study. Both tracks were evaluated with images from the WSRD+ dataset, simulating interactions between self- and cast-shadows with a large number of diverse objects, textures, and materials.

Citations

• NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
• NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
• NTIRE 2025 XGC Quality Assessment Challenge: Methods and Results
• NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution
• NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge
• RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report
• NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results
• NTIRE 2025 challenge on Text to Image Generation Model Quality Assessment
• NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
• NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results
• NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study
• NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results
• NTIRE 2025 Challenge on Image Super-Resolution (×4): Methods and Results
• NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
• NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: Methods and Results
• The Tenth NTIRE 2025 Image Denoising Challenge Report
• NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
• The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
• NTIRE 2025 Challenge on Cross-Domain Few-Shot Object Detection: Methods and Results
• LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors
• ShadowHack: Hacking Shadows via Luminance-Color Divide and Conquer
• ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
• OmniSR: Shadow Removal under Direct and Indirect Lighting
• Frequency-aware Feature Fusion for Dense Image Prediction
• SAM 2: Segment Anything in Images and Videos
• GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval
• Restoring Images in Adverse Weather Conditions via Histogram Transformer
• NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
• ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer
• NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
• The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report
• NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Results
• Towards Image Ambient Lighting Normalization
• LYT-NET: Lightweight YUV Transformer-based Network for Low-light Image Enhancement
• Breaking Through the Haze: An Advanced Non-Homogeneous Dehazing Method based on Fast Fourier Convolution and ConvNeXt
• Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement
• ShadowFormer: Global Context Helps Image Shadow Removal
• ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
• DeS3: Adaptive Attention-driven Self and Soft Shadow Removal using ViT Similarity
• SpA-Former: Transformer image shadow detection and removal via spatial attention
• Simple Baselines for Image Restoration
• Restormer: Efficient Transformer for High-Resolution Image Restoration
• Restormer: Efficient Transformer for High-Resolution Image Restoration
• Masked Autoencoders Are Scalable Vision Learners
• Diffusion Schr "odinger Bridge with Applications to Score-Based\n Generative Modeling
• DW-GAN: A Discrete Wavelet Transform GAN for NonHomogeneous Dehazing
• From Shadow Segmentation to Shadow Removal
• Optimal Transport losses and Sinkhorn algorithm with general convex regularization
• Denoising Diffusion Probabilistic Models
• Shadow Removal via Shadow Image Decomposition
• ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal
• The Unreasonable Effectiveness of Deep Features as a Perceptual Metric
• Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal
• FiLM: Visual Reasoning with a General Conditioning Layer
• Image-to-Image Translation with Conditional Adversarial Networks
• U-Net: Convolutional Networks for Biomedical Image Segmentation
• ImageNet classification with deep convolutional neural networks
• Image quality assessment: from error visibility to structural similarity
• The Retinex Theory of Color Vision
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
• Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Cited by

• NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results
• NTIRE 2025 Challenge on HR Depth from Images of Specular and Transparent Surfaces
• NTIRE 2025 Challenge on RAW Image Restoration and Super-Resolution
• NTIRE 2025 the 2nd Restore Any Image Model (RAIM) in the Wild Challenge
• RAW Image Reconstruction from RGB on Smartphones. NTIRE 2025 Challenge Report
• NTIRE 2025 Challenge on Video Quality Enhancement for Video Conferencing: Datasets, Methods and Results

Related

• NTIRE 2023 Image Shadow Removal Challenge Technical Report: Team IIM_TTI
• Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era
• Soft-Hard Attention U-Net Model and Benchmark Dataset for Multiscale Image Shadow Removal
• Single-Image Shadow Removal Using Deep Learning: A Comprehensive Survey
• No Shadow Left Behind: Removing Objects and their Shadows using Approximate Lighting and Geometry