Search papers, labs, and topics across Lattice.
AnimalLift recovers fully animatable, simulation-ready 3D animals from a single image by predicting canonical geometry, textures, and surface-aligned explicit fur maps over a unified topology. Unlike standard implicit 3D reconstruction models that yield unriggable meshes, this approach explicitly bridges the gap to downstream graphics pipelines by outputting structured UV-parameterized assets. Trained on a large-scale procedural dataset across diverse species, the feed-forward network generalizes effectively to real-world inputs while directly supporting physics-based fur simulation and pose transfer.
Animatable 3D animal assets complete with physically simulatable fur strands can now be reconstructed directly from a single image in a single feed-forward pass.
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.
