Video on BAIR Robot Pushing

Metric: FVD score (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	FVD score▼	Extra Data	Paper	Date↕	Code
1	MoCoGAN	503	No	MoCoGAN: Decomposing Motion and Content for Vide...	2017-07-17	Code
2	Baseline (from LVT)	320.9	No	Latent Video Transformer	2020-06-18	Code
3	SVG-FP (from FVD)	315.5	No	Stochastic Video Generation with a Learned Prior	2018-02-21	Code
4	CDNA (from FVD)	296.5	No	Unsupervised Learning for Physical Interaction t...	2016-05-23	Code
5	SV2P (from FVD)	262.5	No	Stochastic Variational Video Prediction	2017-10-30	Code
6	SVG-LP (from vRNN)	256.62	No	Stochastic Video Generation with a Learned Prior	2018-02-21	Code
7	WAM	159.6	No	Exploring Spatial-Temporal Multi-Frequency Analy...	2020-02-23	Code
8	VRNN 1L	149.22	No	Improved Conditional VRNNs for Video Prediction	2019-04-27	Code
9	SAVP (from vRNN)	143.43	No	Stochastic Adversarial Video Prediction	2018-04-04	Code
10	Hier-VRNN	143.4	No	Improved Conditional VRNNs for Video Prediction	2019-04-27	Code
11	MCVD : c2t5p28	118.4	No	MCVD: Masked Conditional Video Diffusion for Pre...	2022-05-19	Code
12	SAVP (from FVD)	116.4	No	Stochastic Adversarial Video Prediction	2018-04-04	Code
13	DVD-GAN-FP	109.8	No	Adversarial Video Generation on Complex Datasets	2019-07-15	Code
14	VideoGPT	103.3	No	VideoGPT: Video Generation using VQ-VAE and Tran...	2021-04-20	Code
15	TrIVD-GAN-FP	103.3	No	Transformation-based Adversarial Video Predictio...	2020-03-09	-
16	FitVid	93.6	No	FitVid: Overfitting in Pixel-Level Video Predict...	2021-06-24	Code
17	MCVD : c1t5p15	89.5	No	MCVD: Masked Conditional Video Diffusion for Pre...	2022-05-19	Code
18	MCVD : c2t5p14	87.9	No	MCVD: Masked Conditional Video Diffusion for Pre...	2022-05-19	Code
19	NUWA	86.9	Yes	NÜWA: Visual Synthesis Pre-training for Neural v...	2021-11-24	Code
20	RaMViD	84.2	No	Diffusion Models for Video Prediction and Infill...	2022-06-15	Code
21	MAGVIT	62	No	MAGVIT: Masked Generative Video Transformer	2022-12-10	Code

#1MoCoGANSOTA
503
FVD score· 2017-07-17
MoCoGAN: Decomposing Motion and Content for Video Generation Code
#2Baseline (from LVT)
320.9
FVD score· 2020-06-18
Latent Video Transformer Code
#3SVG-FP (from FVD)
315.5
FVD score· 2018-02-21
Stochastic Video Generation with a Learned Prior Code
#4CDNA (from FVD)SOTA
296.5
FVD score· 2016-05-23
Unsupervised Learning for Physical Interaction through Video Prediction Code
#5SV2P (from FVD)
262.5
FVD score· 2017-10-30
Stochastic Variational Video Prediction Code
#6SVG-LP (from vRNN)
256.62
FVD score· 2018-02-21
Stochastic Video Generation with a Learned Prior Code
#7WAM
159.6
FVD score· 2020-02-23
Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction Code
#8VRNN 1L
149.22
FVD score· 2019-04-27
Improved Conditional VRNNs for Video Prediction Code
#9SAVP (from vRNN)
143.43
FVD score· 2018-04-04
Stochastic Adversarial Video Prediction Code
#10Hier-VRNN
143.4
FVD score· 2019-04-27
Improved Conditional VRNNs for Video Prediction Code
#11MCVD : c2t5p28
118.4
FVD score· 2022-05-19
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation Code
#12SAVP (from FVD)
116.4
FVD score· 2018-04-04
Stochastic Adversarial Video Prediction Code
#13DVD-GAN-FP
109.8
FVD score· 2019-07-15
Adversarial Video Generation on Complex Datasets Code
#14VideoGPT
103.3
FVD score· 2021-04-20
VideoGPT: Video Generation using VQ-VAE and Transformers Code
#15TrIVD-GAN-FP
103.3
FVD score· 2020-03-09
Transformation-based Adversarial Video Prediction on Large-Scale Data
#16FitVid
93.6
FVD score· 2021-06-24
FitVid: Overfitting in Pixel-Level Video Prediction Code
#17MCVD : c1t5p15
89.5
FVD score· 2022-05-19
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation Code
#18MCVD : c2t5p14
87.9
FVD score· 2022-05-19
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation Code
#19NUWA
86.9
FVD score· Extra Data· 2021-11-24
NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion Code
#20RaMViD
84.2
FVD score· 2022-06-15
Diffusion Models for Video Prediction and Infilling Code
#21MAGVIT
62
FVD score· 2022-12-10
MAGVIT: Masked Generative Video Transformer Code