Future Video Synthesis with Object Motion Prediction

CVPR 2020  ·  Yue Wu, Rongrong Gao, Jaesik Park, Qifeng Chen ·

We present an approach to predict future video frames given a sequence of continuous video frames in the past. Instead of synthesizing images directly, our approach is designed to understand the complex scene dynamics by decoupling the background scene and moving objects. The appearance of the scene components in the future is predicted by non-rigid deformation of the background and affine transformation of moving objects. The anticipated appearances are combined to create a reasonable video in the future. With this procedure, our method exhibits much less tearing or distortion artifact compared to other approaches. Experimental results on the Cityscapes and KITTI datasets show that our model outperforms the state-of-the-art in terms of visual quality and accuracy.

PDF Abstract CVPR 2020 PDF CVPR 2020 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Video Prediction Cityscapes FVS MS-SSIM 0.8910 # 2
LPIPS 0.0850 # 2
Video Prediction KITTI FVS MS-SSIM 0.7928 # 2
LPIPS 0.1848 # 2


No methods listed for this paper. Add relevant methods here