Research map / Video / Video segmentation and tracking
Video-to-Video Synthesis
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 sequential generator with flow warping and spatio-temporal adversarial learning | video-to-video synthesis · Cityscapes | FID (I3D): 4.66 vs 5.57 (pix2pixHD); 5.55 (COVST) | Helped |
| Use the sequential generator with flow warping and spatio-temporal adversarial learning | video-to-video synthesis · Apolloscape | FID (I3D): 2.24 vs 2.33 (pix2pixHD); 2.36 (COVST) | Helped |
| Use vid2vid for future video prediction via predicted semantic masks | future video prediction · Cityscapes | FID (I3D): 3.44 vs 11.18 (PredNet); 10.00 (MCNet) | Helped |
| Add the foreground-background prior (ablation) | vid2vid · Cityscapes | human preference score: 0.80 / 0.20 | Helped |
| Add the conditional video discriminator (ablation) | vid2vid · Cityscapes | human preference score: 0.84 / 0.16 | Helped |
| Add optical-flow prediction and occlusion-mask-based warping (ablation) | vid2vid · Cityscapes | human preference score: 0.67 / 0.33 | Helped |
Closest papers by meaning
- Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis (CVPR 2024 · similarity 0.89)
- FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis (CVPR 2024 · similarity 0.87)
- OSV: One Step is Enough for High-Quality Image to Video Generation (CVPR 2025 · similarity 0.87)
- BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models (CVPR 2024 · similarity 0.87)
- ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models (CVPR 2024 · similarity 0.87)
- VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis (ICLR 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.