Get the latest tech news

4Real-Video-V2: Feedforward Reconstruction for 4D Scene Generation


pable of computing a 4D spatio-temporal grid of video frames and 3D Gaussian particles for each time step using a feed-forward architecture. Its architecture has two main components, a 4D video diffusion model and a feedforward reconstruction model.

4Real-Video-V2 is capable of computing a 4D spatio-temporal grid of video frames and 3D Gaussian particles for each time step using a feed-forward architecture. This design makes it easily scalable to large pre-trained video models, efficient to train and offers good generalization. We extend our gratitude to Tuan Duc Ngo, Sherwin Bahmani, Jiahao Luo, Hanwen Liang and Guochen Qian for their valuable assistance with data preparation and model training.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of 4d scene generation

4d scene generation