Research Materials

This is where we will keep track of resources we deem to be important.

Project maintained by treese41528 Hosted on GitHub Pages — Theme by mattgraham

Video Generation

To keep track of video generation resources.

Article: ControlVideo: Training-free Controllable Text-to-Video Generation
- ControlVideo
TemporalNet
- Adding Temporal Stability to a Stable Diffusion Render via an automatic1111 extension.
Deforum Website
SD-CN-Animation
- Automate video stylization task using StableDiffusion and ControlNet.
Article: SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation
- Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Article: Structure and Content-Guided Video Synthesis with Diffusion Models
- Structure and content-guided video diffusion model that edits videos based on visual or textual descriptions of the desired output.
mov2mov