A Deeper Look into DeepCap (Invited Paper).
IEEE Trans Pattern Anal Mach Intell
; 45(4): 4009-4022, 2023 Apr.
Article
en En
| MEDLINE
| ID: mdl-34191722
Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or did not recover dense space-time coherent geometry with frame-to-frame correspondences. We propose a novel deep learning approach for monocular dense human performance capture. Our method is trained in a weakly supervised manner based on multi-view supervision completely removing the need for training data with 3D ground truth annotations. The network architecture is based on two separate networks that disentangle the task into a pose estimation and a non-rigid surface deformation step. Extensive qualitative and quantitative evaluations show that our approach outperforms the state of the art in terms of quality and robustness. This work is an extended version of [1] where we provide more detailed explanations, comparisons and results as well as applications.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Tipo de estudio:
Qualitative_research
Idioma:
En
Revista:
IEEE Trans Pattern Anal Mach Intell
Asunto de la revista:
INFORMATICA MEDICA
Año:
2023
Tipo del documento:
Article
Pais de publicación:
Estados Unidos