Skip to main content

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

Xiang, N., Wang, L., Jiang, T., Li, Y., Yang, X. and Zhang, J. J., 2019. Single-image mesh reconstruction and pose estimation via generative normal map. In: CASA '19: 32nd International Conference on Computer Animation and Social Agents, 1-3 July 2019, Paris, France, 79 - 84.

Full text available as:

p79-xiang.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.


DOI: 10.1145/3328756.3328766


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.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:mesh reconstruction, pose estimation, deep learning
Group:Faculty of Media & Communication
ID Code:32587
Deposited By: Symplectic RT2
Deposited On:29 Jul 2019 15:03
Last Modified:14 Mar 2022 14:17


Downloads per month over past year

More statistics for this item...
Repository Staff Only -