pith. sign in

arxiv: 2210.15134 · v2 · pith:EG66ML4Qnew · submitted 2022-10-27 · 💻 cs.CV

Learning Variational Motion Prior for Video-based Motion Capture

classification 💻 cs.CV
keywords motioncapturepriorvideovariationalvideo-baseddatasetsdirectly
0
0 comments X
read the original abstract

Motion capture from a monocular video is fundamental and crucial for us humans to naturally experience and interact with each other in Virtual Reality (VR) and Augmented Reality (AR). However, existing methods still struggle with challenging cases involving self-occlusion and complex poses due to the lack of effective motion prior modeling. In this paper, we present a novel variational motion prior (VMP) learning approach for video-based motion capture to resolve the above issue. Instead of directly building the correspondence between the video and motion domain, We propose to learn a generic latent space for capturing the prior distribution of all natural motions, which serve as the basis for subsequent video-based motion capture tasks. To improve the generalization capacity of prior space, we propose a transformer-based variational autoencoder pretrained over marker-based 3D mocap data, with a novel style-mapping block to boost the generation quality. Afterward, a separate video encoder is attached to the pretrained motion generator for end-to-end fine-tuning over task-specific video datasets. Compared to existing motion prior models, our VMP model serves as a motion rectifier that can effectively reduce temporal jittering and failure modes in frame-wise pose estimation, leading to temporally stable and visually realistic motion capture results. Furthermore, our VMP-based framework models motion at sequence level and can directly generate motion clips in the forward pass, achieving real-time motion capture during inference. Extensive experiments over both public datasets and in-the-wild videos have demonstrated the efficacy and generalization capability of our framework.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation

    cs.CV 2026-06 unverdicted novelty 7.0

    A two-stage generative model (Graph CVAE + flow matching) learns topology-agnostic motion codes from a new 5k-topology dataset and retargets video motion to arbitrary unseen skeletons.

  2. MotionDuet: Dual-Conditioned 3D Human Motion Generation with Video-Regularized Text Learning

    cs.GR 2025-11 unverdicted novelty 6.0

    MotionDuet generates realistic controllable 3D human motions via dual text-video conditioning with DUET unified encoding and DASH distribution-aware loss.