Skip to main content

Rescan: Inductive Instance Segmentation for Indoor RGBD Scans

Author(s): Halber, Maciej; Shi, Yifei; Xu, Kai; Funkhouser, Thomas

To refer to this page use:
Abstract: In depth-sensing applications ranging from home robotics to AR/VR, it will be common to acquire 3D scans of interior spaces repeatedly at sparse time intervals (e.g., as part of regular daily use). We propose an algorithm that analyzes these "rescans'' to infer a temporal model of a scene with semantic instance information. Our algorithm operates inductively by using the temporal model resulting from past observations to infer an instance segmentation of a new scan, which is then used to update the temporal model. The model contains object instance associations across time and thus can be used to track individual objects, even though there are only sparse observations. During experiments with a new benchmark for the new task, our algorithm outperforms alternate approaches based on state-of-the-art networks for semantic instance segmentation.
Publication Date: 2019
Citation: Halber, Maciej, Yifei Shi, Kai Xu, and Thomas Funkhouser. "Rescan: Inductive Instance Segmentation for Indoor RGBD Scans." In IEEE/CVF International Conference on Computer Vision (2019): pp. 2541-2550. doi:10.1109/ICCV.2019.00263
DOI: 10.1109/ICCV.2019.00263
ISSN: 1550-5499
EISSN: 2380-7504
Pages: 2541 - 2550
Type of Material: Conference Article
Journal/Proceeding Title: IEEE/CVF International Conference on Computer Vision
Version: Author's manuscript

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.