Sabathier, R; Mitra, NJ; Novotny, D; (2025) Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videos. In: Leonardis, A and Ricci, E and Roth, S and Russakovsky, O and Sattler, T and Varol, G, (eds.) Computer Vision – ECCV 2024. (pp. pp. 270-287). Springer: Cham, Switzerland.

Text animalAvatar.pdf - Accepted Version Access restricted to UCL open access staff until 3 November 2025. Download (16MB)

Abstract

We present a method to build animatable dog avatars from monocular videos. This is challenging as animals display a range of (unpredictable) non-rigid movements and have a variety of appearance details (e.g., fur, spots, tails). We develop an approach that links the video frames via a 4D solution that jointly solves for animal’s pose variation, and its appearance (in a canonical pose). To this end, we significantly improve the quality of template-based shape fitting by endowing the SMAL parametric model with Continuous Surface Embeddings (CSE), which brings image-to-mesh reprojection constaints that are denser, and thus stronger, than the previously used sparse semantic keypoint correspondences. To model appearance, we propose a novel implicit duplex-mesh texture that is defined in the canonical pose, but can be deformed using SMAL pose coefficients and later rendered to enforce a photometric compatibility with the input video frames. On the challenging CoP3D and APTv2 datasets, we demonstrate superior results (both in terms of pose estimates and predicted appearance) over existing template-free (RAC) and template-based approaches (BARC, BITE). Video results and additional information accessible on the project page: https://remysabathier.github.io/animalavatar.github.io.

Downloads since deposit

Loading...

1Download

Download activity - last month

Export as JSONCSVXML

Loading...

Download activity - last 12 months

Export as JSONCSVXML

Loading...

Downloads by country - last 12 months

Export as JSONCSVXML

Loading...

Archive Staff Only

View Item