Research map / Video / Video segmentation and tracking
One-Trimap Video Matting
Hongje Seong, Seoung Wug Oh, Brian Price, Euntai Kim, Joon-Young Lee
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 |
|---|---|---|---|
| train trimap propagation and alpha prediction jointly rather than decoupled (ablation) | STM+FBA · VideoMatting108 val (1-trimap) | SSDA-V: 83.61 -> 75.36 | Improved |
| add stage-wise training on top of joint training (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 72.07 -> 54.67 | Improved |
| add pretraining stage 1 before end-to-end stage (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 87.31 -> 76.55 | Improved |
| add pretraining stage 2 (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 76.55 -> 75.33 | Improved |
| add pretraining stage 3 (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 75.33 -> 54.67 | Improved |
| add alpha and trimap refinement outputs (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 83.56 -> 77.58 | Improved |
| feed alpha matte to trimap module (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 77.58 -> 62.47 | Improved |
| feed hidden features of refinement module to trimap module (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 62.47 -> 54.67 | Improved |
| use OTVM with DIM backbone instead of STM+DIM | OTVM · VideoMatting108 val (DIM backbone) | SSDA-V: 102.77 -> 92.30 | Improved |
| use OTVM with GCA backbone instead of STM+GCA | OTVM · VideoMatting108 val (GCA backbone) | SSDA-V: 100.22 -> 84.73 | Improved |
| add explicit trimap input to trimap encoder (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 75.08 -> 54.67 | Improved |
| remove trimap input and alpha, keep only hidden for trimap encoder (ablation) | OTVM · VideoMatting108 val (1-trimap) | SSDA-V: 54.67 -> 130.54 | Hurt |
Closest papers by meaning
- End-to-End Video Matting With Trimap Propagation (CVPR 2023 · similarity 0.94)
- Deep Video Matting via Spatio-Temporal Alignment and Aggregation (CVPR 2021 · similarity 0.92)
- Deep Image Matting With Sparse User Interactions (TPAMI 2023 · similarity 0.91)
- Improved Image Matting via Real-Time User Clicks and Uncertainty Estimation (CVPR 2021 · similarity 0.90)
- MatAnyone: Stable Video Matting with Consistent Memory Propagation (CVPR 2025 · similarity 0.88)
- Training Matting Models Without Alpha Labels (AAAI 2025 · 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.
