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

CubeNet: Equivariance to 3D Rotation and Translation

Worrall, D; Brostow, G; (2018) CubeNet: Equivariance to 3D Rotation and Translation. In: Computer Vision – ECCV 2018. (pp. pp. 585-602). Springer: Cham, Switzerland. Green open access

Brostow_CubeNet. Equivariance to 3D Rotation and Translation_AAM.pdf - Accepted version

Download (1MB) | Preview


3D Convolutional Neural Networks are sensitive to transformations applied to their input. This is a problem because a voxelized version of a 3D object, and its rotated clone, will look unrelated to each other after passing through to the last layer of a network. Instead, an idealized model would preserve a meaningful representation of the voxelized object, while explaining the pose-difference between the two inputs. An equivariant representation vector has two components: the invariant identity part, and a discernable encoding of the transformation. Models that can’t explain pose-differences risk “diluting” the representation, in pursuit of optimizing a classification or regression loss function. We introduce a Group Convolutional Neural Network with linear equivariance to translations and right angle rotations in three dimensions. We call this network CubeNet, reflecting its cube-like symmetry. By construction, this network helps preserve a 3D shape’s global and local signature, as it is transformed through successive layers. We apply this network to a variety of 3D inference problems, achieving state-of-the-art on the ModelNet10 classification challenge, and comparable performance on the ISBI 2012 Connectome Segmentation Benchmark. To the best of our knowledge, this is the first 3D rotation equivariant CNN for voxel representations.

Type: Proceedings paper
Title: CubeNet: Equivariance to 3D Rotation and Translation
Event: European Conference on Computer Vision (ECCV 2018)
ISBN-13: 9783030012274
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-01228-1_35
Publisher version: https://doi.org/10.1007/978-3-030-01228-1_35
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.
UCL classification: UCL
UCL > Provost and Vice Provost Offices
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/10075449
Downloads since deposit
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item