Skip to main content
SLU:s publikationsdatabas (SLUpub)

Sammanfattning

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/.

Nyckelord

Animal 3D reconstruction; disentanglement

Publicerad i

Lecture Notes in Computer Science
2025, volym: 15481, sidor: 268-288
Titel: Computer Vision – ACCV 2024 : 17th Asian Conference on Computer Vision, Hanoi, Vietnam, December 8–12, 2024, Proceedings, Part X
Utgivare: Springer Science and Business Media Deutschland GmbH

Konferens

17th Asian Conference on Computer Vision, December 8–12, 2024, Hanoi, Vietnam

SLU författare

UKÄ forskningsämne

Medicinsk biovetenskap

Publikationens identifierare

  • 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 länk till denna sida (URI)

https://res.slu.se/id/publ/142885