UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Escaping plato's cave: 3D shape from adversarial rendering

Henzler, P; Mitra, N; Ritschel, T; (2020) Escaping plato's cave: 3D shape from adversarial rendering. In: Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision (ICCV). (pp. pp. 9983-9992). IEEE: Seoul, South Korea. Green open access

[thumbnail of platonicgan_iccv.pdf]
Preview
Text
platonicgan_iccv.pdf - Accepted version

Download (5MB) | Preview

Abstract

We introduce PlatonicGAN to discover the 3D structure of an object class from an unstructured collection of 2D images, i.e., where no relation between photos is known, except that they are showing instances of the same category. The key idea is to train a deep neural network to generate 3D shapes which, when rendered to images, are indistinguishable from ground truth images (for a discriminator) under various camera poses. Discriminating 2D images instead of 3D shapes allows tapping into unstructured 2D photo collections instead of relying on curated (e.g., aligned, annotated, etc.) 3D data sets. To establish constraints between 2D image observation and their 3D interpretation, we suggest a family of rendering layers that are effectively differentiable. This family includes visual hull, absorption-only (akin to x-ray), and emission-absorption. We can successfully reconstruct 3D shapes from unstructured 2D images and extensively evaluate PlatonicGAN on a range of synthetic and real data sets achieving consistent improvements over baseline methods. We further show that PlatonicGAN can be combined with 3D supervision to improve on and in some cases even surpass the quality of 3D-supervised methods.

Type: Proceedings paper
Title: Escaping plato's cave: 3D shape from adversarial rendering
Event: 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/ICCV.2019.01008
Publisher version: https://doi.org/10.1109/ICCV.2019.01008
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Three-dimensional displays , Two dimensional displays , Shape , Generators , Rendering (computer graphics) , Cameras , Image reconstruction
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10095340
Downloads since deposit
20Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item