Comments (2)
On the one hand, the video compression model takes the latest decoded frame as a reference when encoding and decoding current frame, and the architecture of the video compression model is similar to the Variational Auto-Encoder (VAE). Therefore, if we replace the entropy model and byte stream part with a generative model, such as DiT, then the process of video generation will occur in the latent space of the video compression encoder. At the same time, the whole model can be regarded as an autoregressive video generation model referenced only to the previous generated frame.
On the other hand, as another typical spatio-temporal consistent model, the video compression model includes spatio-temporal information without relying on 3D convolution or spatio-temporal patches, although this is not in line with the technique mentioned by Sora in the technical report. But the method of combining spatio-temporal information to achieve the spatio-temporal consistency is still part of the learning process. Meanwhile, a video generation model based on the video compression model architecture may also be an alternative to Sora in low-computing-power scenarios.
I hope my answer helps.
from minisora.
I will provide a brief answer to your question. Prior to the use of deep learning or AGI for video generation, researchers employed these methods for video compression. In fact, the design of some video compression modules also mimics these standards to a certain extent.
Could you please answer his question in details or in other aspects @fanqiNO1 ?
from minisora.
Related Issues (20)
- Paper link is wrong
- Update equations in `./notes/SD3_zh-CN.md` HOT 1
- [Update] - Standardize the Labels of arXiv Papers [更新] - 标准化arXiv论文的标签 HOT 2
- [Add] - Improved DDPM to Diffusion model
- [Add] - ICML 23 Paper AudioLDM for t2a task
- [Add] - Add VideoMamba
- [Update] - update papers of Audio Related Resource
- [Update] - update papers of Audio Related Resource
- Add ICCV2023 paper `PYoCo` and another paper `VideoFusion` HOT 1
- [Update] - the label of NaturalSpeech 1 & 2
- Add lite-sora to Useful Resources
- Add Pixabay100 dataset
- Update ELLA paper in `Prompt Engineering`
- Update dataset part with respect to #322
- ReCommit PR respect to Issue #255 and PR #342 HOT 1
- Copy ELLA paper to `Diffusion UNet` and `training efficiency` HOT 1
- [Page Update Plans] More user-friendly, More Readable Page with New Features [页面更新计划] 更具用户友好性、可读性更强的新特性主页
- A new video-text dataset which may help HOT 3
- [Update] - update papers of Diffusion model
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from minisora.