SDC-Net: Video prediction using spatially-displaced convolution

We present an approach for high-resolution video frame prediction by conditioning on both past frames and past optical flows. Previous approaches rely on resampling past frames, guided by a learned future optical flow, or on direct generation of pixels... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Video Prediction YouTube-8M SDCNet Average PSNR 37.15 # 1

Methods used in the Paper


METHOD TYPE
Convolution
Convolutions