Stereo Neural Vernier Caliper
Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022
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.
Computer Vision (CV), Intelligent Robotics (ROB), Domain(s) Of Application (APP)
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