CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation

Ci Li, Elin Hernlund, Hedvig Kjellström, Silvia Zuffi
7/1/2024
cs.CV

No confident code implementation found for this paper.

Abstract

In the monocular setting, predicting 3D pose and shape of animals typically relies solely on visual information, which is highly under-constrained. In this work, we explore using audio to enhance 3D shape and motion recovery of horses from monocular video. We test our approach on two datasets: an indoor treadmill dataset for 3D evaluation and an outdoor dataset capturing diverse horse movements, the latter being a contribution to this study. Our results show that incorporating sound with visual data leads to more accurate and robust motion regression. This study is the first to investigate audio's role in 3D animal motion recovery.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Predictive Modeling of Equine Activity Budgets Using a 3D Skeleton Reconstructed from Surveillance Recordings

83% match2023

Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images

82% match2024

DogMo: A Large-Scale Multi-View RGB-D Dataset for 4D Canine Motion Recovery

79% match2025

Benchmarking Monocular 3D Dog Pose Estimation Using In-The-Wild Motion Capture Data

79% match2024

WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation

79% match2026

Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video

79% match2025

Cite this paper

@article{li2024clhop,
  title  = {CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation},
  author = {Ci Li and Elin Hernlund and Hedvig Kjellström and Silvia Zuffi},
  year   = {2024},
  eprint = {2407.01244},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.01244v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.01244.svg)](https://codeofpaper.com/paper/2407.01244)

Discussion