Predicting 3D Human Dynamics from Video
Given a video of a person in action, we can easily guess the 3D future motion of the person. In this work, we present perhaps the first approach for predicting a future 3D mesh model sequence of a person from past video input. We do this for periodic motions such as walking and also actions like bowling and squatting seen in sports or workout videos. While there has been a surge of future prediction problems in computer vision, most approaches predict 3D future from 3D past or 2D future from 2D past inputs. In this work, we focus on the problem of predicting 3D future motion from past image sequences, which has a plethora of practical applications in autonomous systems that must operate safely around people from visual inputs. Inspired by the success of autoregressive models in language modeling tasks, we learn an intermediate latent space on which we predict the future. This effectively facilitates autoregressive predictions when the input differs from the output domain. Our approach can be trained on video sequences obtained in-the-wild without 3D ground truth labels. The project website with videos can be found at https://jasonyzhang.com/phd.
Code (1)
Tasks
3D Human Dynamics3D Human Pose EstimationFuture predictionHuman DynamicsLanguage ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Uncertainty-Aware Human Mesh Recovery From Video by Learning Part-Based 3D Dynamics
Despite the recent success of 3D human reconstruction methods, recovering the accurate and smooth 3D human motion from video is still challenging. Designing a temporal model in the encoding stage is not sufficient en…
3D Human Reconstruction3D ReconstructionDecoderHuman Mesh Recovery+1Unsupervised Learning of Object Structure and Dynamics from Videos
Extracting and predicting object structure and dynamics from videos without supervision is a major challenge in machine learning. To address this challenge, we adopt a keypoint-based image representation and learn a stoc…
Action Recognitioncontinuous-controlContinuous ControlObject+2InterDyn: Controllable Interactive Dynamics with Video Diffusion Models
Predicting the dynamics of interacting objects is essential for both humans and intelligent systems. However, existing approaches are limited to simplified, toy settings and lack generalizability to complex, real-world e…
Video GenerationBehavior-Driven Synthesis of Human Dynamics
Generating and representing human behavior are of major importance for various computer vision applications. Commonly, human video synthesis represents behavior as sequences of postures while directly predicting their li…
Human DynamicsDecomposing Motion and Content for Natural Video Sequence Prediction
We propose a deep neural network for the prediction of future frames in natural video sequences. To effectively handle complex evolution of pixels in videos, we propose to decompose the motion and content, two key compon…
DecoderFuture predictionPredictionVideo Prediction