Research map / Image generation / Image restoration
Towards Image Ambient Lighting Normalization
Florin-Alexandru Vasluianu, Tim Seizinger, Zongwei WU, Rakesh Ranjan, Radu Timofte
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Haar DWT features (ablation) | IFBlend · Ambient6K test | PSNR: 19.624 -> 20.714 | Improved |
| add RGB information splitting (ablation) | IFBlend · Ambient6K test | PSNR: 20.430 -> 20.714 | Improved |
| add SSIM loss term (ablation) | IFBlend · Ambient6K test | SSIM: SSIM 0.792 -> 0.810; PSNR 20.752 -> 20.714 | Mixed |
| use image-frequency shrinkage fusion (IFBlend) vs HINet | IFBlend · Ambient6K test | PSNR: 20.467 -> 20.714 with about 40% fewer MACs | Improved |
| use frequency prior with shrinkage fusion vs other frequency-based methods | IFBlend · Ambient6K test | PSNR: over +0.7 dB PSNR | Improved |
| use mask priors vs mask-free design on shadow removal | shadow removal models · ISTD / ISTD+ | Lab RMSE: ShadowFormer 2.43 vs IFBlend 3.52 on ISTD total | Improved |
| mask-free IFBlend vs ShadowFormer on SRD | IFBlend · SRD | PSNR: 32.38 vs 31.95 | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- HINet — HiNet: Deep Image Hiding by Invertible Network (ICCV 2021) · better on 2 of 2 shared results
- Restormer — Restormer: Efficient Transformer for High-Resolution Image Restoration (CVPR 2022) · better on 1 of 1 shared result
- DCShadowNet — DC-ShadowNet: Single-Image Hard and Soft Shadow Removal Using Unsupervised Domain-Classifier Guided Network (ICCV 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Recasting Regional Lighting for Shadow Removal (AAAI 2024 · similarity 0.90)
- OmniSR: Shadow Removal Under Direct and Indirect Lighting (AAAI 2025 · similarity 0.88)
- When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data (AAAI 2025 · similarity 0.88)
- Detail-Preserving Latent Diffusion for Stable Shadow Removal (CVPR 2025 · similarity 0.87)
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · similarity 0.86)
- Polarization Guided Mask-Free Shadow Removal (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
