Greedy Hierarchical Variational Autoencoders for Large-Scale Video Prediction
Open paper
Benchmark
Model
Rank
Results
video-prediction-on-cityscapes-128x128
GHVAEs
–
FVD: 418.00 ± 5.0
SSIM: 0.740±0.4
LPIPS: 0.193 ± 0.014
Cond.: 2
…
Rank counts only results with a code link.