SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
Summary
SAM 3D Animal introduces a promptable framework for multi-animal 3D reconstruction from single images in the wild, built on the SMAL+ model, achieving state-of-the-art results on multiple datasets.
View Cached Full Text
Cached at: 05/22/26, 06:21 PM
Paper page - SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild
Source: https://huggingface.co/papers/2605.07604
Abstract
SAM 3D Animal enables multi-animal 3D reconstruction from single images using a promptable framework based on SMAL+ model with improved disambiguation through keypoints and masks.
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 firstpromptable frameworkformulti-animal 3D reconstructionfrom a single image. Built on theSMAL+parametric animal model, our method jointly reconstructs multiple instances and supports flexible prompts in the form ofkeypointsandmaskswhich 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 andmodel-free methods, demonstrating a scalable and effective solution for prompt-driven animal 3D reconstruction in the wild.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.07604
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.07604 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.07604 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.07604 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
SAM 3D Body: Robust Full-Body Human Mesh Recovery
SAM 3D Body is a promptable 3D human mesh recovery model using a novel parametric representation (MHR) and encoder-decoder architecture, achieving state-of-the-art performance with strong generalization. The model supports auxiliary prompts and is open-source.
SAM 3: Segment Anything with Concepts
SAM 3 introduces a unified model for promptable concept segmentation and tracking, achieving state-of-the-art performance with a decoupled recognition and localization architecture and a scalable data engine.
@skalskip92: there's no catch; SAM3 is open source and really good one of the things it does really well is object tracking, even in…
SAM3 (Segment Anything Model 3) is open source and performs exceptionally well at object tracking even in complex scenes like basketball, making it a standout computer vision model.
@lillyguisnet: WEEE!!! I had not had the opportunity to try SAM3.1 yet, but simply prompting for "worm" perfectly segmented my images!…
A user shares enthusiastic feedback about SAM 3.1's ability to accurately segment images using simple text prompts like 'worm', highlighting significant improvements over SAM 1.
SAM 3.1: Faster and More Accessible Real-Time Video Detection and Tracking With Multiplexing and Global Reasoning
Meta AI releases SAM 3.1, an update to the Segment Anything Model that enhances real-time video detection and tracking through multiplexing and global reasoning capabilities.