Hernlund, Elin
- Department of Animal Biosciences, Swedish University of Agricultural Sciences
Abstract
In recent years, 3D parametric animal models have been developed to aid in estimating 3D shape and pose from images and video. While progress has been made for humans, it’s more challenging for animals due to limited annotated data. To address this, we introduce the first method using synthetic data generation and disentanglement to learn to regress 3D shape and pose. Focusing on horses, we use text-based texture generation and a synthetic data pipeline to create varied shapes, poses, and appearances, learning disentangled spaces. Our method, Dessie, surpasses existing 3D horse reconstruction methods and generalizes to other large animals like zebras, cows, and deer. See the project website at: https://celiali.github.io/Dessie/.
Keywords
Animal 3D reconstruction; disentanglement
Published in
Lecture Notes in Computer Science
2025, volume: 15481, pages: 268-288
Title: Computer Vision – ACCV 2024 : 17th Asian Conference on Computer Vision, Hanoi, Vietnam, December 8–12, 2024, Proceedings, Part X
Publisher: Springer Science and Business Media Deutschland GmbH
Conference
17th Asian Conference on Computer Vision, December 8–12, 2024, Hanoi, Vietnam
SLU Authors
Kjellström, Hedvig
- Department of Animal Biosciences, Swedish University of Agricultural Sciences
- Royal Institute of Technology (KTH)
- Department of Animal Biosciences, Swedish University of Agricultural Sciences
UKÄ Subject classification
Medical Bioscience
Publication identifier
- DOI: https://doi.org/10.1007/978-981-96-0972-7_16
- ISBN: 978-981-96-0971-0
- eISBN: 978-981-96-0972-7
Permanent link to this page (URI)
https://res.slu.se/id/publ/142885