CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909236206764032 |
|---|---|
| author | Li, Ci Hernlund, Elin Kjellström, Hedvig Zuffi, Silvia |
| author_facet | Li, Ci Hernlund, Elin Kjellström, Hedvig Zuffi, Silvia |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01244 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation Li, Ci Hernlund, Elin Kjellström, Hedvig Zuffi, Silvia Computer Vision and Pattern Recognition 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. |
| title | CLHOP: Combined Audio-Video Learning for Horse 3D Pose and Shape Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.01244 |