Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos

ECCV 2024 (Oral)

Remy Sabathier1,2, Niloy J. Mitra1, David Novotny2,
1University College London, 2Meta
arXiv Code Data ECCV Oral
Main page
Results on scenes from the COP3D Dataset
(Left to right): Original scene, Texture reconstruction in context, Texture reconstruction, Pose reconstruction

Qualitative comparison: Pose


Pose prediction (Left to right): Our, BARC, BITE, RAC.

Qualitative comparison: Texture

Texture reconstruction (Left to right): Our, RAC.