Whole-Body Conditioned Egocentric Video Prediction

• URL: http://arxiv.org/abs/2506.21552v1
• Date: Thu, 26 Jun 2025 17:59:59 GMT
• Title: Whole-Body Conditioned Egocentric Video Prediction
• Authors: Yutong Bai, Danny Tran, Amir Bar, Yann LeCun, Trevor Darrell, Jitendra Malik,
• Abstract summary: We train models to Predict Ego-centric Video from human Actions (PEVA)<n>By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, our model learns to simulate how physical human actions shape the environment from a first-person point of view.<n>Our work represents an initial attempt to tackle the challenges of modeling complex real-world environments and embodied agent behaviors with video prediction from the perspective of a human.
• Score: 98.94980209293776
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We train models to Predict Ego-centric Video from human Actions (PEVA), given the past video and an action represented by the relative 3D body pose. By conditioning on kinematic pose trajectories, structured by the joint hierarchy of the body, our model learns to simulate how physical human actions shape the environment from a first-person point of view. We train an auto-regressive conditional diffusion transformer on Nymeria, a large-scale dataset of real-world egocentric video and body pose capture. We further design a hierarchical evaluation protocol with increasingly challenging tasks, enabling a comprehensive analysis of the model's embodied prediction and control abilities. Our work represents an initial attempt to tackle the challenges of modeling complex real-world environments and embodied agent behaviors with video prediction from the perspective of a human.

Related papers

• Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaption [64.07607726562841]
  Existing multi-person human reconstruction approaches mainly focus on recovering accurate poses or avoiding penetration. In this work, we tackle the task of reconstructing closely interactive humans from a monocular video. We propose to leverage knowledge from proxemic behavior and physics to compensate the lack of visual information.
  arXiv  Detail & Related papers  (2024-04-17T11:55:45Z)
• EgoNav: Egocentric Scene-aware Human Trajectory Prediction [15.346096596482857]
  Wearable collaborative robots stand to assist human wearers who need fall prevention assistance or wear exoskeletons. Such a robot needs to be able to constantly adapt to the surrounding scene based on egocentric vision, and predict the ego motion of the wearer. In this work, we leveraged body-mounted cameras and sensors to anticipate the trajectory of human wearers through complex surroundings.
  arXiv  Detail & Related papers  (2024-03-27T21:43:12Z)
• EgoGen: An Egocentric Synthetic Data Generator [53.32942235801499]
  EgoGen is a new synthetic data generator that can produce accurate and rich ground-truth training data for egocentric perception tasks. At the heart of EgoGen is a novel human motion synthesis model that directly leverages egocentric visual inputs of a virtual human to sense the 3D environment. We demonstrate EgoGen's efficacy in three tasks: mapping and localization for head-mounted cameras, egocentric camera tracking, and human mesh recovery from egocentric views.
  arXiv  Detail & Related papers  (2024-01-16T18:55:22Z)
• Ego-Body Pose Estimation via Ego-Head Pose Estimation [22.08240141115053]
  Estimating 3D human motion from an egocentric video sequence plays a critical role in human behavior understanding and has various applications in VR/AR. We propose a new method, Ego-Body Pose Estimation via Ego-Head Pose Estimation (EgoEgo), which decomposes the problem into two stages, connected by the head motion as an intermediate representation. This disentanglement of head and body pose eliminates the need for training datasets with paired egocentric videos and 3D human motion.
  arXiv  Detail & Related papers  (2022-12-09T02:25:20Z)
• LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies [78.17425779503047]
  We propose a novel neural implicit representation for the human body. It is fully differentiable and optimizable with disentangled shape and pose latent spaces. Our model can be trained and fine-tuned directly on non-watertight raw data with well-designed losses.
  arXiv  Detail & Related papers  (2021-11-30T04:10:57Z)
• Human Performance Capture from Monocular Video in the Wild [50.34917313325813]
  We propose a method capable of capturing the dynamic 3D human shape from a monocular video featuring challenging body poses. Our method outperforms state-of-the-art methods on an in-the-wild human video dataset 3DPW.
  arXiv  Detail & Related papers  (2021-11-29T16:32:41Z)
• Dynamics-Regulated Kinematic Policy for Egocentric Pose Estimation [23.603254270514224]
  We propose a method for object-aware 3D egocentric pose estimation that tightly integrates kinematics modeling, dynamics modeling, and scene object information. We demonstrate for the first time, the ability to estimate physically-plausible 3D human-object interactions using a single wearable camera.
  arXiv  Detail & Related papers  (2021-06-10T17:59:50Z)
• Kinematics-Guided Reinforcement Learning for Object-Aware 3D Ego-Pose Estimation [25.03715978502528]
  We propose a method for incorporating object interaction and human body dynamics into the task of 3D ego-pose estimation. We use a kinematics model of the human body to represent the entire range of human motion, and a dynamics model of the body to interact with objects inside a physics simulator. This is the first work to estimate a physically valid 3D full-body interaction sequence with objects from egocentric videos.
  arXiv  Detail & Related papers  (2020-11-10T00:06:43Z)
• Contact and Human Dynamics from Monocular Video [73.47466545178396]
  Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors. We present a physics-based method for inferring 3D human motion from video sequences that takes initial 2D and 3D pose estimates as input.
  arXiv  Detail & Related papers  (2020-07-22T21:09:11Z)
• Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows [43.89097619822221]
  We present semi-supervised and self-supervised models that support training and good generalization in real-world images and video. Our formulation is based on kinematic latent normalizing flow representations and dynamics, as well as differentiable, semantic body part alignment loss functions. In extensive experiments using 3D motion capture datasets like CMU, Human3.6M, 3DPW, or AMASS, we show that the proposed methods outperform the state of the art.
  arXiv  Detail & Related papers  (2020-03-23T16:11:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.