Animatable 3D animals created from a single image with fur detail
AnimalLift: Reconstructing Animatable 3D Animals from a Single Image by Learning Canonical Shape, Texture, and Fur Maps
Computer Vision and Pattern Recognition
Summary
Turning a single photo of an animal into a fully poseable 3D model is hard, especially if you want the model to move naturally and have editable fur. The authors present AnimalLift, a new method that builds detailed 3D animal shapes with consistent structure, textures, and fur all aligned to a common template. They created a large set of simulated training data to teach their system to do this for many kinds of animals. Their method not only reconstructs animals well but also supports easy animation, changes to fur, and realistic rendering.
What this means in practice
- •For 3d artists and animators: Produce rigged animal models with editable fur from a single image input for animation and visual effects.
- •For game developers: Generate realistic and animatable 3D animal characters quickly for use in interactive environments.
Authors
Chunyi Sun, Ruyi Zha, Weijian Deng, Junlin Han, Dylan Campbell, Stephen Gould
Abstract
Reconstructing a fully animatable 3D animal from a single image remains challenging because animation-ready assets require not only plausible geometry, but also a unified topology, editable appearance, and fur representations compatible with deformation and simulation. Existing image-to-3D approaches often rely on implicit or loosely structured representations that are difficult to rig or edit, while parametric animal models support animation but cannot capture detailed texture and fur appearance. We present AnimalLift, a framework for reconstructing structured, animation-compatible 3D animal assets with explicit fur from a single image. Our method lifts an input image into a shared canonical space with a consistent topology and UV parameterization across the dataset, enabling joint prediction of canonical geometry, texture, and fur in a unified feed-forward architecture. A key component of our representation is a UV-aligned fur map that encodes strand geometry in a surface-aligned canonical domain, allowing explicit fur reconstruction compatible with mesh deformation and fur simulation. To train the model, we introduce a procedural data generation pipeline that provides large-scale supervision with aligned geometry, texture, and fur across diverse animal species and appearances. Experiments on synthetic and real-world datasets demonstrate strong reconstruction quality and generalization across animal categories. Beyond reconstruction, our structured representation directly supports downstream applications including animation, pose transfer, fur editing, and simulation-compatible rendering.