Research map / Detection and segmentation / Open-set and few-shot detection
Learning Non-Lambertian Object Intrinsics Across ShapeNet Categories
Jian Shi, Yue Dong, Hao Su, Stella X. Yu
Check 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 |
|---|---|---|---|
| Use the mirror-link encoder-decoder CNN with separate decoders for albedo, shading, and specular | Non-Lambertian object intrinsics · ShapeNet intrinsics test set | albedo DSSIM: 0.1649 -> 0.0939 | Improved |
| Train Direct Intrinsics on ShapeNet-Intrinsics | Direct Intrinsics · ShapeNet intrinsics test set | albedo DSSIM: 0.1984 -> 0.1655 | Improved |
| Fine-tune the proposed model on MIT data | Ours · MIT intrinsics dataset | albedo DSSIM: 0.1825 -> 0.1465 | Improved |
| Fine-tune the proposed model on MIT data | Ours · MIT intrinsics dataset | shading DSSIM: 0.1667 -> 0.1200 | Improved |
| Train on a category-specific dataset instead of all categories | Non-Lambertian object intrinsics CNN · ShapeNet categories | DSSIM | Improved |
| Freeze the encoder and fine-tune only the decoder on another category (ablation) | Category-trained intrinsics CNN · Cross-category ShapeNet test | DSSIM | No clear effect |
| Use encoder features learned on one category to predict intrinsics in other categories | Non-Lambertian object intrinsics CNN · Cross-category ShapeNet test | DSSIM | No clear effect |
Closest papers by meaning
- A Survey on Intrinsic Images: Delving Deep into Lambert and Beyond (IJCV 2022 · similarity 0.92)
- Self-Supervised Intrinsic Image Decomposition (NeurIPS 2017 · similarity 0.90)
- Revisiting Deep Intrinsic Image Decompositions (CVPR 2018 · similarity 0.89)
- Intrinsic Image Transformation via Scale Space Decomposition (CVPR 2018 · similarity 0.89)
- Unsupervised Learning for Intrinsic Image Decomposition From a Single Image (CVPR 2020 · similarity 0.89)
- ReasonX: MLLM-Guided Intrinsic Image Decomposition (CVPR 2026 · similarity 0.87)
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.
