FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets

2026-09-28

AI Summary

This study addresses the challenge of multi-view realistic and editable animal fur reconstruction caused by the scarcity of dedicated datasets. To overcome this bottleneck, we propose FurE, a method that innovatively leverages human hair data to train a PCA decoder. By integrating defurred body reconstruction with local thickness cues, FurE generates strand geometry through the optimization of a root-conditioned latent field and achieves efficient rendering via a surface-constrained Gaussian frost representation. Experimental results demonstrate that FurE preserves high-fidelity strand details while achieving a 10× training acceleration over existing state-of-the-art methods. Furthermore, its strong generalization capability is validated on both synthetic and real-world sequences.

Abstract

Realistic and editable animal fur reconstruction from multi-view images is challenging due to fine-scale detail, self-occlusion and obfuscation, and, unlike human hair, the lack of animal-fur datasets. Fur usually covers most of an animal's body, with large inter-species and intra-species variability. We present FurE, an efficient strand-based animal fur reconstruction method that recovers a per-strand, editable groom by optimizing a root-conditioned latent field, decoded into strand geometry via a PCA-based decoder. We reconstruct a defurred animal body using local fur-thickness cues from a surface-constrained Gaussian Frosting representation together with part-based priors. We further show that a PCA-based decoder learned from human-hair strand data can alleviate animal-data scarcity while enabling substantially faster optimization. FurE achieves a 10x speedup in strand training over current SOTA dense per-strand optimization while retaining strand fidelity and generalizing across synthetic and real-world sequences, with quantitative and qualitative validation despite the reduction in training time.

Problem

• 3D fur reconstruction
• animal fur
• multi-view images
• dataset scarcity
• strand-based modeling

Innovation

• 3D fur reconstruction
• strand-based optimization
• PCA decoder
• Gaussian Frosting
• cross-domain transfer