Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework

Junkun Jiang, Jie Chen*

*Corresponding author for this work

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

Abstract

Monocular 3D human pose estimation poses significant challenges due to the inherent depth ambiguities that arise during the reprojection process from 2D to 3D. Conventional approaches that rely on estimating an over-fit projection matrix struggle to effectively address these challenges and often result in noisy outputs. Recent advancements in diffusion models have shown promise in incorporating structural priors to address reprojection ambiguities. However, there is still ample room for improvement as these methods often overlook the exploration of correlation between the 2D and 3D joint-level features. In this study, we propose a novel cross-channel embedding framework that aims to fully explore the correlation between joint-level features of 3D coordinates and their 2D projections. In addition, we introduce a context guidance mechanism to facilitate the propagation of joint graph attention across latent channels during the iterative diffusion process. To evaluate the effectiveness of our proposed method, we conduct experiments on two benchmark datasets, namely Human3.6M and MPI-INF-3DHP. Our results demonstrate a significant improvement in terms of reconstruction accuracy compared to state-of-the-art methods. The code for our method will be made available online for further reference.
Original languageEnglish
Title of host publication2024 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - Proceedings
PublisherIEEE
Pages7870-7874
Number of pages5
ISBN (Electronic)9798350344851
ISBN (Print)9798350344868
DOIs
Publication statusPublished - Apr 2024
Event2024 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024 - COEX, Seoul, Korea, Republic of
Duration: 14 Apr 202419 Apr 2024
https://2024.ieeeicassp.org/
https://2024.ieeeicassp.org/program-schedule/
https://ieeexplore.ieee.org/xpl/conhome/10445798/proceeding

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149
ISSN (Electronic)2379-190X

Conference

Conference2024 49th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024
Abbreviated titleICASSP 2024
Country/TerritoryKorea, Republic of
CitySeoul
Period14/04/2419/04/24
Internet address

Scopus Subject Areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

User-Defined Keywords

  • monocular 3D pose estimation
  • diffusion models
  • cross-channel embedding

Fingerprint

Dive into the research topics of 'Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework'. Together they form a unique fingerprint.

Cite this