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

Authors: Xiang, N., Wang, L., Jiang, T., Li, Y., Yang, X. and Zhang, J.

Journal: ACM International Conference Proceeding Series

Pages: 79-84

DOI: 10.1145/3328756.3328766

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.

https://eprints.bournemouth.ac.uk/32587/

Source: Scopus

Single-image Mesh Reconstruction and Pose Estimation via Generative Normal Map

Authors: Xiang, N., Wang, L., Jiang, T., Li, Y., Yang, X. and Zhang, J.

Journal: PROCEEDINGS OF THE 32ND INTERNATIONAL CONFERENCE ON COMPUTER ANIMATION AND SOCIAL AGENTS (CASA 2019)

Pages: 79-84

DOI: 10.1145/3328756.3328766

https://eprints.bournemouth.ac.uk/32587/

Source: Web of Science (Lite)

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

Authors: Xiang, N., Wang, L., Jiang, T., Li, Y., Yang, X. and Zhang, J.J.

Conference: CASA '19: 32nd International Conference on Computer Animation and Social Agents

Pages: 79-84

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.

https://eprints.bournemouth.ac.uk/32587/

Source: BURO EPrints