Abstract: Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a two-stage MOtion, Scene and Object decomposition framework (MOSO) for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSO-Transformer predicts the object and scene tokens of the subsequent video clip based on the previous tokens and adds dynamic motion at the token level to the generated object and scene tokens. Our framework can be easily extended to unconditional video generation and video frame interpolation tasks. Experimental results demonstrate that our method achieves new state-of-the-art performance on five challenging benchmarks for video prediction and unconditional video generation: BAIR, RoboNet, KTH, KITTI and UCF101. In addition, MOSO can produce realistic videos by combining objects and scenes from different videos.
Videos presented on this page are encoded according to H.264 format, which can be displayed through Google Chrome.
Video Prediction on BAIR 64x64
Video Prediction on RoboNet 64x64
Video Prediction on RoboNet 256x256
Video Prediction on KTH 64x64
Video Prediction on KTH 128x128
Video Prediction on KITTI 64x64
Video Prediction on KITTI 256x256