Skip to Main content Skip to Navigation
Conference papers

Data-Driven 3D Reconstruction of Dressed Humans From Sparse Views

Pierre Zins 1 Yuanlu Xu 2 Edmond Boyer 1 Stefanie Wuhrer 1 Tony Tung 2
1 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : Recently, data-driven single-view reconstruction methods have shown great progress in modeling 3D dressed humans. However, such methods suffer heavily from depth ambiguities and occlusions inherent to single view inputs. In this paper, we tackle this problem by considering a small set of input views and investigate the best strategy to suitably exploit information from these views. We propose a data-driven end-to-end approach that reconstructs an implicit 3D representation of dressed humans from sparse camera views. Specifically, we introduce three key components: first a spatially consistent reconstruction that allows for arbitrary placement of the person in the input views using a perspective camera model; second an attention-based fusion layer that learns to aggregate visual information from several viewpoints; and third a mechanism that encodes local 3D patterns under the multi-view context. In the experiments, we show the proposed approach outperforms the state of the art on standard data both quantitatively and qualitatively. To demonstrate the spatially consistent reconstruction, we apply our approach to dynamic scenes. Additionally, we apply our method on real data acquired with a multi-camera platform and demonstrate our approach can obtain results comparable to multi-view stereo with dramatically less views.
Complete list of metadata

https://hal.inria.fr/hal-03385107
Contributor : Pierre Zins Connect in order to contact the contributor
Submitted on : Tuesday, October 19, 2021 - 1:11:18 PM
Last modification on : Tuesday, November 30, 2021 - 6:28:54 PM

File

3DV2021_concat.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03385107, version 1
  • ARXIV : 2104.08013

Collections

Citation

Pierre Zins, Yuanlu Xu, Edmond Boyer, Stefanie Wuhrer, Tony Tung. Data-Driven 3D Reconstruction of Dressed Humans From Sparse Views. 3DV 2021, Dec 2021, London, United Kingdom. ⟨hal-03385107v1⟩

Share

Metrics

Record views

90

Files downloads

64