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

SEETHROUGH: Finding Objects in Heavily Occluded Indoor Scene Images

Hueting, M; Reddy, P; Kim, V; Yumer, E; Carr, N; Mitra, NJ; (2018) SEETHROUGH: Finding Objects in Heavily Occluded Indoor Scene Images. In: (Proceedings) 6th International Conference on 3D Vision (3DV). (pp. pp. 267-276). IEEE: Verona, Italy. Green open access

[thumbnail of Reddy 1710.10473v2.pdf]
Preview
Text
Reddy 1710.10473v2.pdf - Accepted Version

Download (3MB) | Preview

Abstract

Discovering 3D arrangements of objects from single indoor images is important given its many applications such as interior design and content creation for virtual environments. Although heavily researched in the recent years, existing approaches break down under medium to heavy occlusion as the core image-space region detection module fails in absence of directly visible cues. Instead, we take into account holistic contextual 3D information, exploiting the fact that objects in indoor scenes co-occur mostly in typical configurations. First, we use a neural network trained on real indoor annotated images to extract 2D keypoints, and feed them to a 3D candidate object generation stage. Then, we solve a global selection problem among these candidates using pairwise co-occurrence statistics discovered from a large 3D scene database. We iterate the process allowing for candidates with low keypoint response to be incrementally detected based on the location of the already discovered nearby objects. We demonstrate significant performance improvement over combinations of state-of-the-art methods, especially for scenes with moderately to severely occluded objects.

Type: Proceedings paper
Title: SEETHROUGH: Finding Objects in Heavily Occluded Indoor Scene Images
Event: 6th International Conference on 3D Vision (3DV)
Location: Verona, ITALY
Dates: 05 September 2018 - 08 September 2018
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/3DV.2018.00039
Publisher version: https://doi.org/10.1109/3DV.2018.00039
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, Engineering, Electrical & Electronic, Computer Science, Engineering
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/10036763
Downloads since deposit
157Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item