Video Prediction On Kth

評価指標

Cond

FVD

LPIPS

PSNR

Params (M)

Pred

SSIM

Train

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

比較表

モデル名	Cond	FVD	LPIPS	PSNR	Params (M)	Pred	SSIM	Train
stochastic-video-generation-with-a-learned	10	157.9	0.129	23.91	22.8	40	0.800	10
stochastic-adversarial-video-prediction	10	-	-	27.77	-	20	0.852	-
z-order-recurrent-neural-networks-for-video	10	-	-	27.58	-	20	0.817	-
decomposing-motion-and-content-for-natural	10	-	-	26.29	-	20	0.806	-
convolutional-tensor-train-lstm-for-spatio	10	-	0.196	27.62	-	20	0.815	-
diverse-video-generation-using-a-gaussian-1	-	-	-	-	-	-	-	-
video-prediction-recalling-long-term-motion	10	-	159.8	27.5	-	40	0.879	-
slamp-stochastic-latent-appearance-and-motion	10	228 ± 5	0.0795±0.0034	29.39±0.30	-	30	0.8646±0.0050	10
stochastic-variational-video-prediction	10	253.5	0.260	25.70	8.3	40	0.772	10
predrnn-a-recurrent-neural-network-for	10	-	0.139	28.37	-	20	0.839	-
stochastic-latent-residual-video-prediction-1	10	222 ± 3	0.0736±0.0029	29.69±032	-	30	0.8697±0.0046	10
unsupervised-learning-of-object-structure-and	10	395.0	0.124	24.29	2.3	40	0.766	10
convolutional-lstm-network-a-machine-learning	10	-	0.231	23.58	-	20	0.712	-
msnet-mutual-suppression-network-for	10	-	-	27.08	-	20	0.876	-
stochastic-variational-video-prediction	10	209.5	0.232	25.87	8.3	40	0.782	10
stochastic-adversarial-video-prediction	10	145.7	0.116	26.00	7.3	40	0.806	10
varnet-exploring-variations-for-unsupervised	10	-	-	28.48	-	20	0.843	-
dynamic-filter-networks	10	-	-	27.26	-	20	0.794	-
decomposing-motion-and-content-for-natural	10	-	-	25.95	-	20	0.804	-
accurate-grid-keypoint-learning-for-efficient	10	144.2	0.092	27.11	2.0	40	0.837	10
video-pixel-networks	10	-	-	23.76	-	20	0.746	-
stochastic-adversarial-video-prediction	10	183.7	0.126	23.79	17.6	40	0.699	10
deep-learning-for-precipitation-nowcasting-a	10	-	-	26.97	-	20	0.790	-
folded-recurrent-neural-networks-for-future	10	-	-	26.12	-	20	0.771	-
eidetic-3d-lstm-a-model-for-video-prediction	10	-	-	29.31	-	20	0.879	-
stochastic-video-generation-with-a-learned	10	377 ± 6	0.0923±0.0038	28.06±0.29	-	30	0.8438±0.0054	10
predrnn-towards-a-resolution-of-the-deep-in	10	-	-	28.47	-	20	0.865	-
stochastic-adversarial-video-prediction	10	374 ± 3	0.1120±0.0039	26.51±0.29	-	30	0.7564±0.0062	10
exploring-spatial-temporal-multi-frequency	10	-	-	29.85	-	20	0.893	-
stochastic-variational-video-prediction	10	636 ± 1	0.2049±0.0053	28.19±0.31	-	30	0.838	10
video-prediction-at-multiple-scales-with	-	-	0.029	27.81	-	-	0.951	-