Learning single-image 3D reconstruction by generative modelling of shape, pose and shading

Henderson, P. and Ferrari, V. (2020) Learning single-image 3D reconstruction by generative modelling of shape, pose and shading. International Journal of Computer Vision, 128(4), pp. 835-854. (doi: 10.1007/s11263-019-01219-8)

[img] Text
269025.pdf - Published Version
Available under License Creative Commons Attribution.



We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches rely on 3D supervision, annotation of 2D images with keypoints or poses, and/or training with multiple views of each object instance. Our framework is very general: it can be trained in similar settings to existing approaches, while also supporting weaker supervision. Importantly, it can be trained purely from 2D images, without pose annotations, and with only a single view per instance. We employ meshes as an output representation, instead of voxels used in most prior work. This allows us to reason over lighting parameters and exploit shading information during training, which previous 2D-supervised methods cannot. Thus, our method can learn to generate and reconstruct concave object classes. We evaluate our approach in various settings, showing that: (i) it learns to disentangle shape from pose and lighting; (ii) using shading in the loss improves performance compared to just silhouettes; (iii) when using a standard single white light, our model outperforms state-of-the-art 2D-supervised methods, both with and without pose supervision, thanks to exploiting shading cues; (iv) performance improves further when using multiple coloured lights, even approaching that of state-of-the-art 3D-supervised methods; (v) shapes produced by our model capture smooth surfaces and fine details better than voxel-based approaches; and (vi) our approach supports concave classes such as bathtubs and sofas, which methods based on silhouettes cannot learn.

Item Type:Articles
Additional Information:Open access funding provided by Institute of Science and Technology (IST Austria).
Glasgow Author(s) Enlighten ID:Henderson, Dr Paul
Authors: Henderson, P., and Ferrari, V.
College/School:College of Science and Engineering > School of Computing Science
Journal Name:International Journal of Computer Vision
ISSN (Online):1573-1405
Published Online:16 October 2019
Copyright Holders:Copyright © 2019 The Authors
First Published:First published in International Journal of Computer Vision 128(4): 835-854
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record