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

Softmesh: Learning Probabilistic Mesh Connectivity via Image Supervision

Le, ET; Mitra, NJ; Kokkinos, I; (2022) Softmesh: Learning Probabilistic Mesh Connectivity via Image Supervision. In: 2021 International Conference on 3D Vision (3DV). (pp. pp. 1065-1074). IEEE: London,UK. Green open access

[thumbnail of softmesh.pdf]
Preview
PDF
softmesh.pdf - Accepted Version

Download (11MB) | Preview

Abstract

In this work we introduce Softmesh,a fully differentiable pipeline to transform a 3D point cloud into a probabilistic mesh representation that allows us to directly render 2D images. We use this pipeline to learn point connectivity from only 2D rendering supervision,reducing the supervision requirements for mesh-based representations.We evaluate our approach in a set of rendering tasks,including silhouette,normal,and depth rendering on both rigid and non-rigid objects. We introduce transfer learning approaches to handle the diversity of the task requirements,and also explore the potential of learning across categories. We demonstrate that Softmesh achieves competitive performance even against methods trained with full mesh supervision.

Type: Proceedings paper
Title: Softmesh: Learning Probabilistic Mesh Connectivity via Image Supervision
Event: 2021 International Conference on 3D Vision (3DV)
Location: ELECTR NETWORK
Dates: 1 Dec 2021 - 3 Dec 2021
ISBN-13: 9781665426886
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/3DV53792.2021.00114
Publisher version: https://doi.org/10.1109/3DV53792.2021.00114
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: Science & Technology, Technology, Computer Science, Artificial Intelligence, Computer Science, Software Engineering, Engineering, Electrical & Electronic, Imaging Science & Photographic Technology, Computer Science, Engineering
UCL classification: 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
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL
URI: https://discovery.ucl.ac.uk/id/eprint/10149389
Downloads since deposit
118Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item