2025-04-09 スウェーデン王立工科大学(KTH)
<関連情報>
- https://www.kth.se/en/om/nyheter/centrala-nyheter/ai-helps-decode-horse-body-language-for-better-veterinary-care-1.1394028
- https://arxiv.org/abs/2410.03438
- https://celiali.github.io/Dessie/
デッシー 画像から関節を持つ3D馬の形状と姿勢を推定するためのディセンタングルメント Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images
Ci Li, Yi Yang, Zehang Weng, Elin Hernlund, Silvia Zuffi, Hedvig Kjellström
arXiv last revised 31 Oct 2024 (this version, v2)
DOI:https://doi.org/10.48550/arXiv.2410.03438
Abstract
In recent years, 3D parametric animal models have been developed to aid in estimating 3D shape and pose from images and video. While progress has been made for humans, it’s more challenging for animals due to limited annotated data. To address this, we introduce the first method using synthetic data generation and disentanglement to learn to regress 3D shape and pose. Focusing on horses, we use text-based texture generation and a synthetic data pipeline to create varied shapes, poses, and appearances, learning disentangled spaces. Our method, Dessie, surpasses existing 3D horse reconstruction methods and generalizes to other large animals like zebras, cows, and deer.
