FurE: Efficient Instance-Specific 3D Fur Reconstruction without Animal-Fur Datasets
FurE is presented, 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, and shows that a PCA-based decoder learned from human-hair strand data can alleviate animal-data s...
Srinjay Sarkar, Prakhar Kaushik, Soumava Paul et al.
· 0 citations