OpenCodePapers

video-prediction-on-kinetics-600-12-frames

Video Prediction
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodeFVDISCondPredModelNameReleaseDate
Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion2.3511SiD22024-10-25
Photorealistic Video Generation with Diffusion Models3.3W.A.L.T.-L2023-12-11
Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation✓ Link4.3±0.1MAGVIT-v22023-10-09
LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior✓ Link5.1511LARP2024-10-28
MAGVIT: Masked Generative Video Transformer✓ Link9.9±0.3511MAGVIT (-L-FP)2022-12-10
Scalable Adaptive Computation for Iterative Generation✓ Link10.817.7RIN (1000 steps)2022-12-22
Scalable Adaptive Computation for Iterative Generation✓ Link11.517.7RIN (400 steps)2022-12-22
Diffusion Models for Video Prediction and Infilling✓ Link16.46511RaMViD2022-06-15
MAGVIT: Masked Generative Video Transformer✓ Link24.5±0.9511MAGVIT (-B-FP)2022-12-10
Transformation-based Adversarial Video Prediction on Large-Scale Data25.74±0.6612.54±0.06511TriVD-GAN-FP2020-03-09
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation✓ Link32.9OmniTokenizer-AR2024-06-13
CCVS: Context-aware Controllable Video Synthesis✓ Link55±1511CCVS2021-07-16
Predicting Video with VQVAE✓ Link64.30±2.04412Video VQ-VAE FVD2021-03-02
Adversarial Video Generation on Complex Datasets✓ Link69.15±0.78511DVD-GAN-FP2019-07-15
Scaling Autoregressive Video Models✓ Link170±5511Video Transformer2019-06-06
Latent Video Transformer✓ Link224.73511LVT2020-06-18