分阶段迭代修复阴影，结合语义与几何信息，获CVPR2026挑战赛冠军。
Winner of CVPR2026 NTIRE Challenge on Image Shadow Removal: Semantic and Geometric Guidance for Shadow Removal via Cascaded Refinement
- 三阶段级联优化，逐轮修正前阶段残留伪影。
- 在WSRD+测试集上达26.680 PSNR，FID仅26.135，排名第一。
- 适合需要高精度去阴影的图像修复与计算机视觉应用。
我们提出一种三阶段渐进式去阴影流水线，用于CVPR2026 NTIRE WSRD+挑战赛。基于OmniSR框架，该方法将去阴影视为迭代直接修复过程，后阶段修正前阶段预测留下的残余伪影。模型融合RGB外观、冻结的DINOv2语义引导，以及来自单目深度和表面法向的几何线索，并在所有阶段复用。为稳定多阶段优化，引入收缩约束目标函数，确保重建误差在级联中非递增。采用分阶段训练策略，从早期WSRD预训练迁移至WSRD+监督，最终通过余弦退火检查点集成完成WSRD+ 2026适配。在官方的WSRD+ 2026隐藏测试集上，最终集成模型达到26.680 PSNR、0.8740 SSIM、0.0578 LPIPS和26.135 FID，整体排名第一，赢得NTIRE 2026图像去阴影挑战赛。模型在ISTD+和UAV-SC+数据集上也展现出强泛化能力。
原文摘要 · Abstract (English)
We present a three-stage progressive shadow-removal pipeline for the CVPR2026 NTIRE WSRD+ challenge. Built on OmniSR, our method treats deshadowing as iterative direct refinement, where later stages correct residual artefacts left by earlier predictions. The model combines RGB appearance with frozen DINOv2 semantic guidance and geometric cues from monocular depth and surface normals, reused across all stages. To stabilise multi-stage optimisation, we introduce a contraction-constrained objective that encourages non-increasing reconstruction error across the cascade. A staged training pipeline transfers from earlier WSRD pretraining to WSRD+ supervision and final WSRD+ 2026 adaptation with cosine-annealed checkpoint ensembling. On the official WSRD+ 2026 hidden test set, our final ensemble achieved 26.680 PSNR, 0.8740 SSIM, 0.0578 LPIPS, and 26.135 FID, ranked first overall, and won the NTIRE 2026 Image Shadow Removal Challenge. The strong performance of the proposed model is further validated on the ISTD+ and UAV-SC+ datasets.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。