Summary of Progressive Autoregressive Video Diffusion Models, by Desai Xie et al.
Progressive Autoregressive Video Diffusion Models
by Desai Xie, Zhan Xu, Yicong Hong, Hao Tan, Difan Liu, Feng Liu, Arie Kaufman, Yang Zhou
First submitted to arxiv on: 10 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed autoregressive video diffusion models can generate high-quality long videos by extending current frontier video diffusion models. This is achieved by assigning progressively increasing noise levels to latent frames, allowing for fine-grained condition among the latents and large overlaps between attention windows. The progressive video denoising enables the model to autoregressively generate video frames without quality degradation or abrupt scene changes. State-of-the-art results are presented on long video generation at 1 minute (1440 frames at 24 FPS). |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Autoregressive video diffusion models can create high-quality videos for a longer time than before. This is possible by changing the way we add noise to the images being generated, allowing them to be more connected and overlapping. This new approach helps keep the quality of the generated video consistent without sudden changes in the scene. The model achieves state-of-the-art results in generating 1-minute long videos. |
Keywords
» Artificial intelligence » Attention » Autoregressive
