Single-image mesh reconstruction and pose estimation via generative normal map

Nan Xiang, Li Wang, Tao Jiang, Yanran Li, Xiaosong Yang*, Jianjun Zhang

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

6 Citations (Scopus)

Abstract

We present a unified learning framework for recovering both 3D mesh and camera pose of the object from a single image. Our approach learns to recover outer shape and surface geometric details of the mesh without relying on 3D supervision. We adopt multi-view normal maps as the 2D supervision so that the silhouette and geometric details information can be transferred to neural network. A normal mismatch based objective function is introduced to train the network, and the camera pose is parameterized into the objective, it integrates pose estimation with the mesh reconstruction in a same optimization procedure. We demonstrate the abilities of the proposed approach in generating 3D mesh and estimating camera pose with qualitative and quantitative experiments.

Original languageEnglish
Title of host publicationProceedings of the 32nd International Conference on Computer Animation and Social Agents, CASA 2019
PublisherAssociation for Computing Machinery
Pages79-84
Number of pages6
ISBN (Electronic)9781450371599
DOIs
Publication statusPublished - 1 Jul 2019
Externally publishedYes
Event32nd International Conference on Computer Animation and Social Agents, CASA 2019 - Paris, France
Duration: 1 Jul 20193 Jul 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference32nd International Conference on Computer Animation and Social Agents, CASA 2019
Country/TerritoryFrance
CityParis
Period1/07/193/07/19

Keywords

  • Deep learning
  • Mesh reconstruction
  • Pose estimation

Cite this