Research map / Video / Video segmentation and tracking
BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-Based Video Colorization
Yixin Yang, Jinshan Pan, Zhongzheng Peng, Xiaoyu Du, Zhulin Tao, Jinhui Tang
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 bidirectional temporal fusion block (BTFB) instead of average weighting (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 28.32 -> 30.40 | Improved |
| add BTFB instead of average weighting (ablation) | BiSTNet · DAVIS (synthetic) | CDC: 0.004359 -> 0.003540 | Improved |
| add segmentation mask m_t^s in MEB (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 27.58 -> 30.40 | Improved |
| add edge mask m_t^e in MEB (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 27.99 -> 30.40 | Improved |
| add both masks (MEB) (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 26.61 -> 30.40 | Improved |
| add both masks (MEB) (ablation) | BiSTNet · DAVIS (synthetic) | CDC: 0.003972 -> 0.003540 | Improved |
| add multi-scale recurrent block (MSRB) (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 27.29 -> 30.40 | Improved |
| add multi-scale recurrent block (MSRB) (ablation) | BiSTNet · DAVIS (synthetic) | CDC: 0.004640 -> 0.003540 | Improved |
| add edge loss (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 28.15 -> 30.40 | Improved |
| add hard example mining loss (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 27.08 -> 30.40 | Improved |
| add both edge and hard example mining losses (ablation) | BiSTNet · DAVIS (synthetic) | PSNR: 27.00 -> 30.40 | Improved |
| use two reference exemplars instead of one | BiSTNet · DAVIS (synthetic) | PSNR: 29.07 -> 30.40 | Improved |
Closest papers by meaning
- Deep Exemplar-Based Video Colorization (CVPR 2019 · similarity 0.92)
- Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization (ECCV 2022 · similarity 0.89)
- ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization (ECCV 2024 · similarity 0.88)
- Stylization-Based Architecture for Fast Deep Exemplar Colorization (CVPR 2020 · similarity 0.88)
- Pixelated Semantic Colorization (IJCV 2019 · similarity 0.87)
- ChromaFusionNet (CFNet): Natural Fusion of Fine-Grained Color Editing (AAAI 2024 · similarity 0.84)
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.
