Research map / Video / Video segmentation and tracking
Shortcut-V2V: Compression Framework for Video-to-Video Translation Based on Temporal Redundancy Reduction
Chaeyeon Chung, Yeojeong Park, Seunghwan Choi, Munkhsoyol Ganbat, Jaegul Choo
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 reference (previous-frame) features to the Shortcut block (ablation) | Shortcut-V2V · vid2vid Edge->Face (E2F) | FVD: 0.398 -> 0.209 | Improved |
| add current-frame encoder features to the Shortcut block (ablation) | Shortcut-V2V · Unsup Viper->Cityscapes (V2C) | FVD: 1.249 -> 1.180 | Improved |
| use coarse-to-fine alignment instead of single-stage alignment (ablation) | Shortcut-V2V · Unsup Viper->Cityscapes (V2C) | FVD: 1.195 -> 1.180 | Improved |
| use coarse-to-fine alignment instead of single-stage alignment (ablation) | Shortcut-V2V · vid2vid Edge->Face (E2F) | FVD: 0.213 -> 0.209 | Improved |
| use adaptive blending mask instead of element-wise addition (ablation) | Shortcut-V2V (AdaBD) · vid2vid Edge->Face (E2F) | FVD: 0.244 -> 0.209 | Improved |
| use higher teacher model dependence (ablation) | Shortcut-V2V · vid2vid Edge->Face (E2F) | FVD: 0.277 -> 0.193 | Improved |
| compress with Shortcut-V2V instead of image-based CAT/OMGD | Unsup Viper->Label (V2L) · Unsup Viper->Label (V2L) | mIoU: 9.76 -> 11.5 | Improved |
| compress with Shortcut-V2V instead of Fast-Vid2Vid | vid2vid Label->Cityscapes (L2C) · vid2vid Label->Cityscapes (L2C) | FVD: 0.310 -> 0.165 | Improved |
| compress original vid2vid with Shortcut-V2V | vid2vid Edge->Face (E2F) · vid2vid Edge->Face (E2F) | FVD: 0.186 -> 0.209 | Hurt |
| compress original Unsup with Shortcut-V2V | Unsup Viper->Cityscapes (V2C) · Unsup Viper->Cityscapes (V2C) | FVD: 1.253 -> 1.180 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Fast-Vid2Vid — Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis (ECCV 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Looking Backward: Streaming Video-to-Video Translation with Feature Banks (ICLR 2025 · similarity 0.87)
- PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models (CVPR 2025 · similarity 0.86)
- One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding (NeurIPS 2025 · similarity 0.86)
- DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models (CVPR 2025 · similarity 0.85)
- LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding (ICML 2025 · similarity 0.85)
- Neural Video Compression with Context Modulation (CVPR 2025 · similarity 0.85)
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.
