SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild

Hugging Face Daily Papers Papers

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.

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.
Original Article
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

Papers with Code Trending

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

Papers with Code Trending

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.