Research map / Video / Video segmentation and tracking
End-To-End Time-Lapse Video Synthesis From a Single Outdoor Image
Check 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 multi-frame joint conditional generation with shared sequence context instead of a vanilla cGAN (ablation) | Time-lapse synthesis model · Outdoor time-lapse synthesis | illumination-change quality | Helped |
| add multi-domain training with TLVDB alongside AMOS (ablation) | Multi-frame joint conditional GAN · Outdoor time-lapse synthesis | color-tone quality | Helped |
| use multi-frame joint conditional generation instead of a vanilla cGAN (ablation) | Time-lapse synthesis model · Outdoor time-lapse synthesis | illumination-change quality | Helped |
| use the proposed method instead of Shih et al. [27] | Time-lapse synthesis · TLVDB test images, user study | perceived as real (%): 44.9% -> 60.6% | Helped |
| use the proposed method instead of Li et al. [19] | Time-lapse synthesis · TLVDB test images, user study | perceived as real (%): 34.1% -> 60.6% | Helped |
Closest papers by meaning
- Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks (CVPR 2018 · similarity 0.91)
- Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis (CVPR 2024 · similarity 0.84)
- ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation (NeurIPS 2024 · similarity 0.84)
- BIVDiff: A Training-Free Framework for General-Purpose Video Synthesis via Bridging Image and Video Diffusion Models (CVPR 2024 · similarity 0.84)
- FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention (NeurIPS 2024 · similarity 0.84)
- Generative Inbetweening through Frame-wise Conditions-Driven Video Generation (CVPR 2025 · 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.