Research map / Video / Video generation
Stochastic Video Generation with a Learned Prior
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 a learned time-varying prior instead of a fixed Gaussian prior (ablation) | SVG · Stochastic Moving MNIST | SSIM | Helped |
| Use a learned time-varying prior instead of a fixed Gaussian prior (ablation) | SVG · KTH Action Dataset | SSIM | No clear effect |
| Use stochastic latent variables with a fixed or learned prior instead of omitting latent variables | Video frame predictor · Stochastic Moving MNIST | SSIM | Helped |
| Use stochastic latent variables with a fixed or learned prior instead of omitting latent variables | Video frame predictor · KTH Action Dataset | SSIM | Helped |
| Use SVG-FP or SVG-LP instead of the compared state-of-the-art approach | BAIR robot pushing dataset · BAIR robot pushing dataset | SSIM | Helped |
| Use SVG-LP instead of the compared state-of-the-art approach | BAIR robot pushing dataset · BAIR robot pushing dataset | PSNR | Mixed |
Closest papers by meaning
- WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors (NeurIPS 2026 · similarity 0.87)
- Learning World Models for Interactive Video Generation (NeurIPS 2025 · similarity 0.86)
- Video-Mirai: Autoregressive Video Diffusion Models Need Foresight (NeurIPS 2026 · similarity 0.86)
- From Slow Bidirectional to Fast Autoregressive Video Diffusion Models (CVPR 2025 · similarity 0.86)
- WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception (NeurIPS 2025 · similarity 0.85)
- Autoregressive Video Generation without Vector Quantization (ICLR 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.