PointAE: Point Auto-Encoder for 3D Statistical Shape and Texture Modelling

Hang Dai, Ling Shao; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 5410-5419

Abstract


The outcome of standard statistical shape modelling is a vector space representation of objects. Any convex combination of vectors of a set of object class examples generates a real and valid example. In this paper, we propose a Point Auto-Encoder (PointAE) with skip-connection, attention blocks for 3D statistical shape modelling directly on 3D points. The proposed PointAE is able to refine the correspondence with a correspondence refinement block. The data with refined correspondence can be fed to the PointAE again and bootstrap the constructed statistical models. Instead of two seperate models, PointAE can simultaneously model the shape and texture variation. The extensive evaluation in three open-sourced datasets demonstrates that the proposed method achieves better performance in representation ability of the shape variations.

Related Material


[pdf]
[bibtex]
@InProceedings{Dai_2019_ICCV,
author = {Dai, Hang and Shao, Ling},
title = {PointAE: Point Auto-Encoder for 3D Statistical Shape and Texture Modelling},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}