| title | SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild |
|---|---|
| authors | Xuyi Hu, Jin Lyu, Jiuming Liu, Yebin Liu, Silvia Zuffi, Liang An, Stefan Goetz |
| date | 2026-05-08 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.07604 |
| upvotes | 3 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scenes, while existing methods predominantly focus on single-animal settings. We present SAM 3D Animal, the first promptable framework for multi-animal 3D reconstruction from a single image. Built on the SMAL+ parametric animal model, our method jointly reconstructs multiple instances and supports flexible prompts in the form of keypoints and masks which enable more reliable disambiguation in crowded and occluded scenes. To train such a model, we further introduce Herd3D, a multi-animal 3D dataset containing over 5K images, designed to increase diversity in species, interactions, and occlusion patterns. Experiments on the Animal3D, APTv2, and Animal Kingdom datasets show that our framework achieves state-of-the-art results over both existing model-based and model-free methods, demonstrating a scalable and effective solution for prompt-driven animal 3D reconstruction in the wild. |
cite
@misc{hu2026sam,
title={SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild},
author={Xuyi Hu and Jin Lyu and Jiuming Liu and Yebin Liu and Silvia Zuffi and Liang An and Stefan Goetz},
year={2026},
eprint={2605.07604},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.07604}
}