Research map / Label-efficient and robust learning / Self-supervised and contrastive
Self-Supervised Intrinsic Image Decomposition
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 |
|---|---|---|---|
| Use reconstruction error on raw unlabeled images to adapt shape representations | RIN · Unseen shapes | shape prediction error: 29% improvement | Helped |
| Use reconstruction error on raw unlabeled images to adapt lighting representations | RIN · New lighting conditions | light prediction error: 18% improvement | Helped |
| Use reconstruction error on unlabeled target images to update reflectance and shading representations | RIN · Airplanes to automobiles | reflectance and shading representation quality | Helped |
Closest papers by meaning
- Unsupervised Learning for Intrinsic Image Decomposition From a Single Image (CVPR 2020 · similarity 0.93)
- Revisiting Deep Intrinsic Image Decompositions (CVPR 2018 · similarity 0.92)
- When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data (AAAI 2025 · similarity 0.88)
- Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces (AAAI 2025 · similarity 0.86)
- ReasonX: MLLM-Guided Intrinsic Image Decomposition (CVPR 2026 · similarity 0.86)
- Latent Intrinsics Emerge from Training to Relight (NeurIPS 2024 · 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.