Research map / Image generation / Editing and style transfer
Clair Obscur: an Illumination-Aware Method for Real-World Image Vectorization
Xingyue Lin, Shuai Peng, Xiangyu Xie, Jianhua Zhu, Yuxuan Zhou, Liangcai Gao
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 |
|---|---|---|---|
| initialize albedo layer from intrinsic albedo map masks (ablation) | COVec · Qualitative (Fig. 11) | layer separation | Improved |
| region-wise semantic binarization vs global, OTSU, adaptive thresholding (ablation) | COVec illumination init · Qualitative (Fig. 12) | shadow region alignment | Improved |
| region-wise semantic binarization for emoji initialization (ablation) | COVec simplified variant · Emoji (Fig. 13) | shape detail | Improved |
| add reconstruction loss to structure loss (ablation) | COVec · Qualitative (Fig. 14) | color accuracy | Improved |
| add structure loss to reconstruction loss (ablation) | COVec · Qualitative (Fig. 14) | vector boundary regularity | Improved |
Closest papers by meaning
- Optimize & Reduce: A Top-Down Approach for Image Vectorization (AAAI 2024 · similarity 0.87)
- Less is More: Efficient Image Vectorization with Adaptive Parameterization (CVPR 2025 · similarity 0.87)
- Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport (ICLR 2025 · similarity 0.85)
- Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation (CVPR 2025 · similarity 0.84)
- Layered Image Vectorization via Semantic Simplification (CVPR 2025 · similarity 0.84)
- Latent Intrinsics Emerge from Training to Relight (NeurIPS 2024 · similarity 0.83)
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.
