Papers with Code · CC BY-SA 4.0

BAIR Robot Pushing

아카이브 평가 31건 · 마지막 적재/변경 2026-10-30

평가 기록

과거 수집 기록이며 최신 순위가 아닙니다. 데이터셋 버전·split·실험 조건과 지표 방향이 검증되지 않은 결과는 직접 비교할 수 없습니다. 날짜는 논문 날짜이며 최신 평가일을 뜻하지 않습니다.

표가 화면보다 넓으면 좌우로 스크롤하여 논문과 구현 링크를 확인하세요.

원본 기록 순서 · 순위 미부여
모델	원본 지표·값	논문	구현
MAGVIT	FVD score 62 Cond 1 Pred 15 Train 15	MAGVIT: Masked Generative Video Transformer 2022-12-10	코드 1
RaMViD	FVD score 84.20 Cond 1 Pred 15 Train 20	Diffusion Models for Video Prediction and Infilling 2022-06-15	코드 1
NUWA	FVD score 86.9 Cond 1 Pred 15 Train 15	NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion 2021-11-24	코드 1
MCVD : c2t5p14	FVD score 87.9 Cond 2 SSIM 0.838 PSNR 19.1 Pred 14 Train 5	MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation 2022-05-19	코드 1 · 코드 2
MCVD : c1t5p15	FVD score 89.5 Cond 1 SSIM 0.78 PSNR 16.9 Pred 15 Train 5	MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation 2022-05-19	코드 1 · 코드 2
FitVid	FVD score 93.6 Cond 1 Pred 15 Train 15 Notes Uses 100 times more fake than real samples (atypical)	FitVid: Overfitting in Pixel-Level Video Prediction 2021-06-24	코드 1
Video Transformer	FVD score 94± 2 Cond 1 Pred 15 Train 15 Notes FVD on only leftmost samples is 94, FVD on unrolled (all subsequences) is 96	Scaling Autoregressive Video Models 2019-06-06	코드 1
CCVS	FVD score 99 ± 2 Cond 1 Pred 15 Train 15	CCVS: Context-aware Controllable Video Synthesis 2021-07-16	코드 1
VideoGPT	FVD score 103.3 Cond 1 Pred 15 Train 15	VideoGPT: Video Generation using VQ-VAE and Transformers 2021-04-20	코드 1 · 코드 2 · 코드 3
TrIVD-GAN-FP	FVD score 103.3 Cond 1 Pred 15 Train 15	Transformation-based Adversarial Video Prediction on Large-Scale Data 2020-03-09	연결 없음
DVD-GAN-FP	FVD score 109.8 Cond 1 Pred 15 Train 15	Adversarial Video Generation on Complex Datasets 2019-07-15	코드 1
SAVP (from FVD)	FVD score 116.4 Cond 2 Pred 14 Train 14	Stochastic Adversarial Video Prediction 2018-04-04	코드 1 · 코드 2 · 코드 3 · 코드 4
MCVD : c2t5p28	FVD score 118.4 Cond 2 SSIM 0.745 PSNR 16.2 Pred 28 Train 5	MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation 2022-05-19	코드 1 · 코드 2
LVT	FVD score 125.76±2.90 Cond 1 Pred 15 Train 15	Latent Video Transformer 2020-06-18	코드 1
VideoFlow	FVD score 131±5 Cond 3 Pred 14 (total 16) Train 10	VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation 2019-03-04	코드 1
Hier-VRNN	FVD score 143.4 Cond 2 SSIM 0.822±0.06 LPIPS 0.055±0.03 Pred 28 Train 10	Improved Conditional VRNNs for Video Prediction 2019-04-27	코드 1
SAVP (from vRNN)	FVD score 143.43 Cond 2 SSIM 0.795±0.07 LPIPS 0.062±0.03 Pred 28 Train 10	Stochastic Adversarial Video Prediction 2018-04-04	코드 1 · 코드 2 · 코드 3 · 코드 4
VRNN 1L	FVD score 149.22 Cond 2 SSIM 0.829±0.06 LPIPS 0.058±0.03 Pred 28 Train 10	Improved Conditional VRNNs for Video Prediction 2019-04-27	코드 1
SAVP (from SRVP)	FVD score 152±9 Cond 2 SSIM 0.7887±0.0092 PSNR 18.44±0.25 LPIPS 0.0634±0.0026 Pred 28 Train 12	Stochastic Adversarial Video Prediction 2018-04-04	코드 1 · 코드 2 · 코드 3 · 코드 4
WAM	FVD score 159.6 Cond 2 SSIM 0.844 PSNR 21.02 LPIPS 0.0936 Pred 28 Train 14	Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction 2020-02-23	코드 1
SRVP	FVD score 162 ± 4 Cond 2 SSIM 0.8196±0.0084 PSNR 19.59±0.27 LPIPS 0.0574±0.0032 Pred 28 Train 12	Stochastic Latent Residual Video Prediction 2020-02-21	코드 1
SLAMP	FVD score 245 ± 5 Cond 2 SSIM 0.8175±0.084 PSNR 19.67±0.26 LPIPS 0.0596±0.0032 Pred 28 Train 10	SLAMP: Stochastic Latent Appearance and Motion Prediction 2021-08-05	코드 1
SVG (from SRVP)	FVD score 255±4 Cond 2 SSIM 0.8058±0.0088 PSNR 18.95±0.26 LPIPS 0.0609±0.0034 Pred 28 Train 12	Stochastic Video Generation with a Learned Prior 2018-02-21	코드 1 · 코드 2 · 코드 3
SVG-LP (from vRNN)	FVD score 256.62 Cond 2 SSIM 0.816±0.07 LPIPS 0.061±0.03 Pred 28 Train 10	Stochastic Video Generation with a Learned Prior 2018-02-21	코드 1 · 코드 2 · 코드 3
SV2P (from FVD)	FVD score 262.5 Cond 2 Pred 14 Train 14	Stochastic Variational Video Prediction 2017-10-30	코드 1 · 코드 2 · 코드 3
CDNA (from FVD)	FVD score 296.5 Cond 2 Pred 14 Train 14	Unsupervised Learning for Physical Interaction through Video Prediction 2016-05-23	코드 1 · 코드 2
SVG-FP (from FVD)	FVD score 315.5 Cond 2 Pred 14 Train 14	Stochastic Video Generation with a Learned Prior 2018-02-21	코드 1 · 코드 2 · 코드 3
Baseline (from LVT)	FVD score 320.9 Cond 1 Pred 15 Train 15	Latent Video Transformer 2020-06-18	코드 1
MoCoGAN	FVD score 503 Cond 4 Pred 12 Train 12	MoCoGAN: Decomposing Motion and Content for Video Generation 2017-07-17	코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5
SV2P (from SRVP)	FVD score 965±17 Cond 2 SSIM 0.8169±0.0086 PSNR 20.39±0.27 LPIPS 0.0912±0.0053 Pred 28 Train 12	Stochastic Variational Video Prediction 2017-10-30	코드 1 · 코드 2 · 코드 3