Research map / Video / Video segmentation and tracking
DTVNet: Dynamic Time-lapse Video Generation via Single Still Image
Jiangning Zhang, Chao Xu, Liang Liu, Mengmeng Wang, Xia Wu, Yong Liu, Yunliang Jiang
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 motion loss to content loss (ablation) | DTVNet · Sky Time-lapse | PSNR: 28.768 -> 29.364 | Improved |
| add motion loss to content loss (ablation) | DTVNet · Sky Time-lapse | Flow-MSE: 1.624 -> 1.509 | Improved |
| add motion loss to content loss (ablation) | DTVNet · Sky Time-lapse | SSIM: 0.897 -> 0.906 | Improved |
| add adversarial loss to content and motion losses (ablation) | DTVNet · Sky Time-lapse | PSNR: 29.364 -> 29.917 | Improved |
| add adversarial loss to content and motion losses (ablation) | DTVNet · Sky Time-lapse | Flow-MSE: 1.509 -> 1.275 | Improved |
| add adversarial loss to content and motion losses (ablation) | DTVNet · Sky Time-lapse | SSIM: 0.906 -> 0.916 | Improved |
| add the optical flow encoder (OFE) (ablation) | DTVNet · Sky Time-lapse | qualitative frame motion | Improved |
| use DTVNet instead of MoCoGAN | DTVNet · Sky Time-lapse | PSNR: 23.867 -> 29.917 | Improved |
| use DTVNet instead of MDGAN | DTVNet · Sky Time-lapse | PSNR: 23.042 -> 29.917 | 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.
- MoCoGAN — MoCoGAN: Decomposing Motion and Content for Video Generation (CVPR 2018) · better on 3 of 3 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
- Decouple Content and Motion for Conditional Image-to-Video Generation (AAAI 2024 · similarity 0.84)
- ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation (NeurIPS 2024 · similarity 0.84)
- Modular-Cam: Modular Dynamic Camera-view Video Generation with LLM (AAAI 2025 · similarity 0.84)
- Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think (CVPR 2025 · similarity 0.83)
- Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs (CVPR 2024 · similarity 0.83)
- VidTwin: Video VAE with Decoupled Structure and Dynamics (CVPR 2025 · similarity 0.83)
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.
