Skip to main content
Article
CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection
arXiv
  • Dhanalaxmi Gaddam, Mohamed bin Zayed University of Artificial Intelligence
  • Jean Lahoud, Mohamed bin Zayed University of Artificial Intelligence
  • Fahad Shahbaz Khan, Mohamed bin Zayed University of Artificial Intelligence & Linköping University, Sweden
  • Rao Anwer, Mohamed bin Zayed University of Artificial Intelligence & Aalto University, Finland
  • Hisham Cholakkal, Mohamed bin Zayed University of Artificial Intelligence
Document Type
Article
Abstract

Existing deep learning-based 3D object detectors typically rely on the appearance of individual objects and do not explicitly pay attention to the rich contextual information of the scene. In this work, we propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework, which takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene at multiple levels to predict a set of object bounding-boxes along with their corresponding semantic labels. To this end, we propose to utilize a context enhancement network that captures the contextual information at different levels of granularity followed by a multi-stage refinement module to progressively refine the box positions and class predictions. Extensive experiments on the large-scale ScanNetV2 benchmark reveal the benefits of our proposed method, leading to an absolute improvement of 2.0% over the baseline. In addition to 3D object detection, we investigate the effectiveness of our CMR3D framework for the problem of 3D object counting. Our source code will be publicly released. © 2022, CC BY.

DOI
10.48550/arXiv.2209.06641
Publication Date
9-13-2022
Keywords
  • Deep learning,
  • Object recognition,
  • Semantics
Comments

Preprint: arXiv

Archived with thanks to arXiv

Preprint License: CC by 4.0

Uploaded 31 October 2022

Citation Information
D. Gaddam, J. Lahoud, F.S. Khan, R.M. Anwer, and H. Cholakkal, "CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection", 2022, doi:10.48550/arXiv.2209.06641