Research map / Video / Video segmentation and tracking
Deep Exemplar-Based Video Colorization
Bo Zhang, Mingming He, Jing Liao, Pedro V. Sander, Lu Yuan, Amine Bermak, Dong Chen
Check 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 |
|---|---|---|---|
| Use the full exemplar-guided recurrent colorization network rather than the strongest listed image-colorization baseline | Deep Exemplar-Based Video Colorization · ImageNet 10k | FID: 4.78 -> 4.02 | Improved |
| Add adversarial loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | Colorful: 14.93 -> 17.90 | Improved |
| Add adversarial loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | Top-1 Acc(%): 65.46 -> 64.64 | Hurt |
| Add perceptual loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | FID: 5.23 -> 4.02 | Improved |
| Add contextual loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | FID: 6.06 -> 4.02 | Improved |
| Add smoothness loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | FID: 4.12 -> 4.02 | Improved |
| Add contextual loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | Top-1 Acc(%): 62.96 -> 64.64 | Improved |
| Add perceptual loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | Colorful: 18.44 -> 17.90 | Hurt |
| Add contextual loss (ablation) | Deep Exemplar-Based Video Colorization · ImageNet 10k | Colorful: 18.94 -> 17.90 | Hurt |
| Learn correspondence parameters instead of nearest-neighbor feature matching (ablation) | Deep Exemplar-Based Video Colorization · Video colorization | matching quality | Improved |
| Use recurrent reference guidance in place of propagation-only video colorization | Deep Exemplar-Based Video Colorization · DAVIS video propagation | PSNR stability | Improved |
| Use video adversarial training rather than omitting adversarial loss (ablation) | Deep Exemplar-Based Video Colorization · Video colorization | visual realism | Improved |
Closest papers by meaning
- BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-Based Video Colorization (TPAMI 2024 · similarity 0.92)
- Stylization-Based Architecture for Fast Deep Exemplar Colorization (CVPR 2020 · similarity 0.90)
- Semantic-Sparse Colorization Network for Deep Exemplar-Based Colorization (ECCV 2022 · similarity 0.89)
- Fully Automatic Video Colorization With Self-Regularization and Diversity (CVPR 2019 · similarity 0.89)
- Learned Variational Video Color Propagation (ECCV 2022 · similarity 0.88)
- ColorMNet: A Memory-based Deep Spatial-Temporal Feature Propagation Network for Video Colorization (ECCV 2024 · similarity 0.88)
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.
