ステレオニューラルノギス：インスタンス単位の3D物体検出フレームワーク
Stereo Neural Vernier Caliper
初期3D直方体推定を局所的に精緻化するインスタンス単位モデルを提案し、粗から細へのマルチ解像度化やモデル非依存の位置補正、ステレオ3D追跡を実現してKITTIで最高性能を達成した。
著者: Shichao Li, Zechun Liu, Zhiqiang Shen, Kwang-Ting Cheng
分類: cs.CV, cs.RO
原文アブストラクト
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.
