Video Prediction
19개 벤치마크 · 논문 470편 · 이 태스크의 논문 보기 →
Benchmarks
KTH
Moving MNIST
Human3.6M
BAIR Robot Pushing
Cityscapes 128x128
SynpickVP
CMU Mocap-2
Cityscapes
KITTI
Vimeo90K
CMU Mocap-1
DAVIS 2017
Colored dSprites
KTH 64x64 cond10 pred30
MPI Sintel
Something-Something V2
Sprites
YouTube-8M
Most implemented
Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
Video-to-Video Synthesis
MogaNet: Multi-order Gated Aggregation Network
Video Diffusion Models
Papers
ActiveWAM: Evidence-Aware Active Vision for World-Action Models
Active vision manipulation requires a policy to control both its camera and its end-effectors, yet camera motion determines which evidence remains visible within finite observation windows. Acquiring a new view can displ…
Video PredictionMinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception
Modeling spatiotemporal coupling is a key challenge in building physical intelligence across scales, from microscopic to macroscopic. Existing models capture such structure broadly through physics-motivated dynamical for…
Video PredictionXPACE: Joint World and Action Modeling from Heterogeneous Experience
A general-purpose robot needs to draw on diverse experience, choose actions, and anticipate how those actions will change the world. We introduce XPACE, a unified embodied world model that serves as both a world action m…
Video PredictionGeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human Videos
Human videos provide rich manipulation experience, but extracting action representations that preserve useful motion remains challenging. Visual reconstruction alone can entangle manipulation-related motion with appearan…
Video PredictionVideo GenerationAcrossVAM1.0: Particle World Modeling for Text-Assisted Robot Video Prediction
Predicting robot videos requires both precise motion reasoning and preservation of high-frequency appearance, yet monolithic pixel models entangle these objectives and often conceal their progress behind a strong last-fr…
Video PredictionDECOWAM: Decoupled Whole-Body World-Action Model for Legged Mobile Manipulation
Mobile manipulation requires a robot to predict how locomotion and arm motion jointly alter future observations and control. Existing world-action models, developed largely for fixed-base platforms, do not explicitly dis…
Video Prediction