Research map / Video / Video generation
VideoVAE+: Large Motion Video Autoencoding with Cross-modal Video VAE
Yazhou Xing, Yang Fei, Yingqing He, Jingye Chen, Jiaxin Xie, Xiaowei Chi, Qifeng Chen
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 |
|---|---|---|---|
| use two-stage temporal-aware spatial plus temporal compression instead of simultaneous (ablation) | Video VAE · Large Motion test | PSNR: 24.0593 -> 24.6722 | Improved |
| use two-stage compression instead of sequential (ablation) | Video VAE · Large Motion test | PSNR: 23.3681 -> 24.6722 | Improved |
| use two-stage compression instead of simultaneous (ablation) | Video VAE · Large Motion test | LPIPS: 0.1293 -> 0.1162 | Improved |
| use two-stage compression instead of simultaneous (ablation) | Video VAE · Large Motion test | SSIM: 0.7315 -> 0.7234 | Hurt |
| add image-video joint training (ablation) | Video VAE 4-channel · WebVid test | PSNR: 30.2091 -> 30.3140 | Improved |
| add image-video joint training (ablation) | Video VAE 16-channel · WebVid test | PSNR: 33.8844 -> 34.1558 | Improved |
| add image-video joint training (ablation) | Video VAE 4-channel · Image reconstruction | PSNR: 15.1001 -> 30.8650 | Improved |
| add image-video joint training (ablation) | Video VAE 16-channel · Image reconstruction | PSNR: 9.2603 -> 35.3437 | Improved |
| add cross-modal text guidance (ablation) | Video VAE 16-channel · WebVid test | PSNR: 34.1558 -> 34.5022 | Improved |
| add cross-modal text guidance (ablation) | Video VAE 4-channel · WebVid test | PSNR: 30.3140 -> 30.1110 | Hurt |
| add cross-modal text guidance (ablation) | Video VAE 16-channel · WebVid test | LPIPS: 0.0271 -> 0.0323 | Hurt |
| use video GAN loss instead of image GAN loss (ablation) | temporal-aware spatial autoencoder · MMTrailer val | PSNR: 31.9133 -> 32.0262 | Improved |
Closest papers by meaning
- Improved Video VAE for Latent Video Diffusion Model (CVPR 2025 · similarity 0.92)
- WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model (CVPR 2025 · similarity 0.91)
- CV-VAE: A Compatible Video VAE for Latent Generative Video Models (NeurIPS 2024 · similarity 0.90)
- VidTwin: Video VAE with Decoupled Structure and Dynamics (CVPR 2025 · similarity 0.89)
- MotionAura: Generating High-Quality and Motion Consistent Videos using Discrete Diffusion (ICLR 2025 · similarity 0.88)
- SSC-VAE: Structured Sparse Coding Based Variational Autoencoder for Detail Preserved Image Reconstruction (AAAI 2025 · similarity 0.87)
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.
