Research map / Video / Video generation
Hierarchical Video Generation From Orthogonal Information: Optical Flow and Texture
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 |
|---|---|---|---|
| Fuse flow-discriminator and texture-discriminator features with a Linear SVM | FTGAN · UCF101 | accuracy: 60.9% | Helped |
| Use the flow-discriminator representation | FTGAN · UCF101 | accuracy: 49.5% | Helped |
| Use the texture-discriminator representation | FTGAN · UCF101 | accuracy: 50.5% | Helped |
| Generate appearance from ground-truth optical flow with TextureGAN instead of VGAN | TextureGAN · SURREAL | worker preference over VGAN: 44% | Hurt |
| Generate appearance from ground-truth optical flow with TextureGAN instead of VGAN | TextureGAN · Penn Action | worker preference over VGAN: 72% | Helped |
| Generate video hierarchically from generated optical flow and texture | FTGAN · SURREAL | worker preference over VGAN: 54% | Helped |
| Generate video hierarchically from generated optical flow and texture | FTGAN · Penn Action | worker preference over VGAN: 58% | Helped |
Closest papers by meaning
- Generating Videos with Scene Dynamics (NeurIPS 2016 · similarity 0.89)
- MoCoGAN: Decomposing Motion and Content for Video Generation (CVPR 2018 · similarity 0.89)
- Self-Supervised Video GANs: Learning for Appearance Consistency and Motion Coherency (CVPR 2021 · similarity 0.89)
- Taming generative video models for zero-shot optical flow extraction (NeurIPS 2025 · similarity 0.85)
- Goku: Flow Based Video Generative Foundation Models (CVPR 2025 · similarity 0.85)
- LAMP: Learn A Motion Pattern for Few-Shot Video Generation (CVPR 2024 · 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.