3 papers
cs.CV2025
MatteViT: High-Frequency-Aware Document Shadow Removal with Shadow Matte Guidance
Chaewon Kim, Seoyeon Lee, Jonghyuk Park
Document shadow removal is essential for enhancing the clarity of digitized documents. Preserving high-frequency details (e.g., text edges and lines) is critical in this process be…
cs.CV2025
Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps
Seoyeon Lee, Gwangyeol Yu, Chaewon Kim +1
Diffusion models have achieved remarkable success in image synthesis. However, addressing artifacts and unrealistic regions remains a critical challenge. We propose self-refining d…
cs.CV2025
NTIRE 2025 Image Shadow Removal Challenge Report
Florin-Alexandru Vasluianu, Tim Seizinger, Zhuyun Zhou +79
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 durin…