Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Karnoor, Sahil Bhandary, Choudhury, Romit Roy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917482395074560
author Karnoor, Sahil Bhandary
Choudhury, Romit Roy
author_facet Karnoor, Sahil Bhandary
Choudhury, Romit Roy
contents Pose estimation refers to tracking a human's full body posture, including their head, torso, arms, and legs. The problem is challenging in practical settings where the number of body sensors are limited. Past work has shown promising results using conditional diffusion models, where the pose prediction is conditioned on both <location, rotation> measurements from the sensors. Unfortunately, nearly all these approaches generalize poorly across users, primarly because location measurements are highly influenced by the body size of the user. In this paper, we formulate pose estimation as an inverse problem and design an algorithm capable of zero-shot generalization. Our idea utilizes a pre-trained diffusion model and conditions it on rotational measurements alone; the priors from this model are then guided by a likelihood term, derived from the measured locations. Thus, given any user, our proposed InPose method generatively estimates the highly likely sequence of poses that best explains the sparse on-body measurements.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02043
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers
Karnoor, Sahil Bhandary
Choudhury, Romit Roy
Computer Vision and Pattern Recognition
Human-Computer Interaction
Machine Learning
Pose estimation refers to tracking a human's full body posture, including their head, torso, arms, and legs. The problem is challenging in practical settings where the number of body sensors are limited. Past work has shown promising results using conditional diffusion models, where the pose prediction is conditioned on both <location, rotation> measurements from the sensors. Unfortunately, nearly all these approaches generalize poorly across users, primarly because location measurements are highly influenced by the body size of the user. In this paper, we formulate pose estimation as an inverse problem and design an algorithm capable of zero-shot generalization. Our idea utilizes a pre-trained diffusion model and conditions it on rotational measurements alone; the priors from this model are then guided by a likelihood term, derived from the measured locations. Thus, given any user, our proposed InPose method generatively estimates the highly likely sequence of poses that best explains the sparse on-body measurements.
title Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers
topic Computer Vision and Pattern Recognition
Human-Computer Interaction
Machine Learning
url https://arxiv.org/abs/2510.02043