Research map / 3D vision / 3D generation
Shading Annotations in the Wild
Check 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 |
|---|---|---|---|
| Train a CNN on SAW shading annotations | Shading classifier · SAW test set | precision @ 30% recall: 0.977 -> 0.946 | Hurt |
| Train a CNN on SAW shading annotations | Shading classifier · SAW test set | precision @ 50% recall: 0.949 -> 0.938 | Hurt |
| Train a CNN on SAW shading annotations | Shading classifier · SAW test set | precision @ 70% recall: 0.868 -> 0.845 | Hurt |
| Fine-tune all network layers instead of only the last three fully-connected layers (ablation) | SAW shading CNN · Validation set | validation performance | Hurt |
| Fine-tune only the last fully-connected layer instead of the last three fully-connected layers (ablation) | SAW shading CNN · Validation set | validation performance | Hurt |
Closest papers by meaning
- Learning Intrinsic Image Decomposition From Watching the World (CVPR 2018 · similarity 0.85)
- Self-Supervised Intrinsic Image Decomposition (NeurIPS 2017 · similarity 0.85)
- Gaussian Shadow Casting for Neural Characters (CVPR 2024 · similarity 0.84)
- RNG: Relightable Neural Gaussians (CVPR 2025 · similarity 0.83)
- SpecNeRF: Gaussian Directional Encoding for Specular Reflections (CVPR 2024 · similarity 0.83)
- When Shadow Removal Meets Intrinsic Image Decomposition: A Joint Learning Framework Using Unpaired Data (AAAI 2025 · similarity 0.82)
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.