Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment

• URL: http://arxiv.org/abs/2404.09499v1
• Date: Mon, 15 Apr 2024 06:38:09 GMT
• Title: Learning Human Motion from Monocular Videos via Cross-Modal Manifold Alignment
• Authors: Shuaiying Hou, Hongyu Tao, Junheng Fang, Changqing Zou, Hujun Bao, Weiwei Xu,
• Abstract summary: Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics. We present the Video-to-Motion Generator (VTM), which leverages motion priors through cross-modal latent feature space alignment. The VTM showcases state-of-the-art performance in reconstructing 3D human motion from monocular videos.
• Score: 45.74813582690906
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning 3D human motion from 2D inputs is a fundamental task in the realms of computer vision and computer graphics. Many previous methods grapple with this inherently ambiguous task by introducing motion priors into the learning process. However, these approaches face difficulties in defining the complete configurations of such priors or training a robust model. In this paper, we present the Video-to-Motion Generator (VTM), which leverages motion priors through cross-modal latent feature space alignment between 3D human motion and 2D inputs, namely videos and 2D keypoints. To reduce the complexity of modeling motion priors, we model the motion data separately for the upper and lower body parts. Additionally, we align the motion data with a scale-invariant virtual skeleton to mitigate the interference of human skeleton variations to the motion priors. Evaluated on AIST++, the VTM showcases state-of-the-art performance in reconstructing 3D human motion from monocular videos. Notably, our VTM exhibits the capabilities for generalization to unseen view angles and in-the-wild videos.

Related papers

• SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering [45.51684124904457]
  We propose a new 4D motion paradigm, SurMo, that models the temporal dynamics and human appearances in a unified framework. Surface-based motion encoding that models 4D human motions with an efficient compact surface-based triplane. Physical motion decoding that is designed to encourage physical motion learning. 4D appearance modeling that renders the motion triplanes into images by an efficient surface-conditioned decoding.
  arXiv  Detail & Related papers  (2024-04-01T16:34:27Z)
• Cinematic Behavior Transfer via NeRF-based Differentiable Filming [63.1622492808519]
  Existing SLAM methods face limitations in dynamic scenes and human pose estimation often focuses on 2D projections. We first introduce a reverse filming behavior estimation technique. We then introduce a cinematic transfer pipeline that is able to transfer various shot types to a new 2D video or a 3D virtual environment.
  arXiv  Detail & Related papers  (2023-11-29T15:56:58Z)
• MotionBERT: A Unified Perspective on Learning Human Motion Representations [46.67364057245364]
  We present a unified perspective on tackling various human-centric video tasks by learning human motion representations from large-scale and heterogeneous data resources. We propose a pretraining stage in which a motion encoder is trained to recover the underlying 3D motion from noisy partial 2D observations. We implement motion encoder with a Dual-stream Spatio-temporal Transformer (DSTformer) neural network.
  arXiv  Detail & Related papers  (2022-10-12T19:46:25Z)
• 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)
• Action2video: Generating Videos of Human 3D Actions [31.665831044217363]
  We aim to tackle the interesting yet challenging problem of generating videos of diverse and natural human motions from prescribed action categories. Key issue lies in the ability to synthesize multiple distinct motion sequences that are realistic in their visual appearances. Action2motionally generates plausible 3D pose sequences of a prescribed action category, which are processed and rendered by motion2video to form 2D videos.
  arXiv  Detail & Related papers  (2021-11-12T20:20:37Z)
• 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)
• Motion Guided 3D Pose Estimation from Videos [81.14443206968444]
  We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose. In computing motion loss, a simple yet effective representation for keypoint motion, called pairwise motion encoding, is introduced. We design a new graph convolutional network architecture, U-shaped GCN (UGCN), which captures both short-term and long-term motion information.
  arXiv  Detail & Related papers  (2020-04-29T06:59:30Z)

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.