Research map / Detection and segmentation / Open-set and few-shot detection
TOM-Net: Learning Transparent Object Matting From a Single Image
Guanying Chen, Kai Han, Kwan-Yee K. Wong
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 |
|---|---|---|---|
| add flow regression loss to CoarseNet (ablation) | CoarseNet · Synthetic validation set (excluding Complex Shape) | F-EPE (whole image / object region): 3.9 / 26.5 -> 2.2 / 15.4 | Improved |
| add image reconstruction loss to CoarseNet (ablation) | CoarseNet · Synthetic validation set (excluding Complex Shape) | I-MSE: 0.22 -> 0.18 | Improved |
| add multi-scale loss to CoarseNet (ablation) | CoarseNet · Synthetic validation set (excluding Complex Shape) | M-IoU: 0.94 -> 0.97 | Improved |
| add cross-link to CoarseNet (ablation) | CoarseNet · Synthetic validation set (excluding Complex Shape) | F-EPE (whole image / object region): 2.5 / 17.2 -> 2.2 / 15.4 | Improved |
| add RefineNet to CoarseNet (ablation) | CoarseNet · Synthetic validation set (excluding Complex Shape) | F-EPE (whole image / object region): 2.2 / 15.4 -> 2.0 / 13.7 | Improved |
| add RefineNet to CoarseNet (ablation) | CoarseNet · Real test set, Average | PSNR: 21.91 -> 21.84 | No clear effect |
Closest papers by meaning
- Learning Transparent Object Matting (IJCV 2019 · similarity 0.99)
- TransMatting: Enhancing Transparent Objects Matting with Transformers (ECCV 2022 · similarity 0.90)
- Image Matting without Matting-Specific Annotations via Eikonal Fields (NeurIPS 2026 · similarity 0.88)
- Learning-Based Sampling for Natural Image Matting (CVPR 2019 · similarity 0.88)
- DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting (NeurIPS 2024 · similarity 0.87)
- Training Matting Models Without Alpha Labels (AAAI 2025 · 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.
