Research map / Label-efficient and robust learning / Recognition and long-tail
Revisiting Deep Intrinsic Image Decompositions
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 the Domain Filter and learned guidance map (ablation) | Ours · IIW test split | WHDR (mean): 15.40 -> 14.45 | Helped |
| use joint training of the entire pipeline (ablation) | Ours · IIW test split | WHDR (mean): 14.52 -> 14.45 | Helped |
| train jointly on IIW and MPI data | Ours · IIW | WHDR (mean): 14.45 -> 15.80 | Hurt |
| train jointly on IIW and MPI data | Ours · new real-world outdoor images | reflectance smoothness | Helped |
Closest papers by meaning
- Unsupervised Learning for Intrinsic Image Decomposition From a Single Image (CVPR 2020 · similarity 0.92)
- Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces (AAAI 2025 · similarity 0.87)
- Deep Unfolded Network with Intrinsic Supervision for Pan-Sharpening (AAAI 2024 · similarity 0.86)
- ReasonX: MLLM-Guided Intrinsic Image Decomposition (CVPR 2026 · similarity 0.86)
- When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data (AAAI 2025 · similarity 0.85)
- SSUN-Net: Spatial-Spectral Prior-Aware Unfolding Network for Pan-Sharpening (AAAI 2025 · similarity 0.85)
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.