Stereo Neural Vernier Caliper

Authors

Shichao Li, Hong Kong University of Science and Technology
Zechun Liu, Hong Kong University of Science and Technology & Carnegie Mellon University
Zhiqiang Shen, Hong Kong University of Science and Technology & Carnegie Mellon University & Mohamed bin Zayed University of Artificial IntelligenceFollow
Kwang Ting Cheng, Hong Kong University of Science and Technology

Document Type

Conference Proceeding

Publication Title

Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022

Abstract

We propose a new object-centric framework for learning-based stereo 3D object detection. Previous studies build scene-centric representations that do not consider the significant variation among outdoor instances and thus lack the flexibility and functionalities that an instance-level model can offer. We build such an instance-level model by formulating and tackling a local update problem, i.e., how to predict a refined update given an initial 3D cuboid guess. We demonstrate how solving this problem can complement scene-centric approaches in (i) building a coarse-to-fine multi-resolution system, (ii) performing model-agnostic object location refinement and, (iii) conducting stereo 3D tracking-by-detection. Extensive experiments demonstrate the effectiveness of our approach, which achieves state-of-the-art performance on the KITTI benchmark. Code and pre-trained models are available at https://github.com/Nicholasli1995/SNVC.

First Page

1376

Last Page

1385

DOI

10.1609/aaai.v36i2.20026

Publication Date

6-28-2022

Keywords

Computer Vision (CV), Intelligent Robotics (ROB), Domain(s) Of Application (APP)

Comments

IR conditions: non-described

Recommended Citation

S. Li, Z. Liu, Z. Shen, and K.-T. Cheng, “Stereo Neural Vernier Caliper”, AAAI, vol. 36, no. 2, pp. 1376-1385, Jun. 2022, doi: 10.1609/aaai.v36i2.20026