Research map / Video / Video generation
Non-Adversarial Video Synthesis With Learned Priors
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 learned latent vectors rather than random latent vectors (ablation) | Video synthesis method · Chair-CAD | MCS: 3.96 to 3.32 | Helped |
| Use learned latent vectors rather than random latent vectors (ablation) | Video synthesis method · Chair-CAD | FCS: 0.75 to 0.89 | Helped |
| Add both triplet loss and static loss (ablation) | Video synthesis method · Chair-CAD | MCS: 3.83 to 3.32 | Helped |
| Add both triplet loss and static loss (ablation) | Video synthesis method · Chair-CAD | FCS: 0.77 to 0.89 | Helped |
| Add static loss while retaining triplet loss (ablation) | Video synthesis method · Chair-CAD | FCS: 0.81 to 0.89 | Helped |
| Add static loss while retaining triplet loss (ablation) | Video synthesis method · Chair-CAD | MCS: 3.36 to 3.32 | Helped |
| Add triplet loss while retaining static loss (ablation) | Video synthesis method · Chair-CAD | MCS: 3.82 to 3.32 | Helped |
| Add triplet loss while retaining static loss (ablation) | Video synthesis method · Chair-CAD | FCS: 0.85 to 0.89 | Helped |
| Use the proposed method instead of MoCoGAN | Video synthesis · Chair-CAD | MCS: 4.11 -> 3.32 | Helped |
| Use the proposed method instead of MoCoGAN | Video synthesis · Weizmann Human Action | MCS: 3.41 -> 2.63 | Helped |
| Use the proposed method instead of VGAN | Video synthesis · Golf | MCS: 3.61 -> 2.71 | Helped |
| Use the proposed method instead of VGAN | Video synthesis · Golf | FCS: 0.88 -> 0.84 | Hurt |
Closest papers by meaning
- Video-to-Video Synthesis (NeurIPS 2018 · similarity 0.88)
- SF-V: Single Forward Video Generation Model (NeurIPS 2024 · similarity 0.88)
- OSV: One Step is Enough for High-Quality Image to Video Generation (CVPR 2025 · similarity 0.87)
- Diffusion Adversarial Post-Training for One-Step Video Generation (ICML 2025 · similarity 0.86)
- Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation (NeurIPS 2025 · similarity 0.86)
- FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling (ICLR 2024 · 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.