论文标题
立体神经游标卡钳
Stereo Neural Vernier Caliper
论文作者
论文摘要
我们为基于学习的立体声3D对象检测提供了一个新的以对象为中心的框架。先前的研究建立了以场景为中心的表示，这些表示不考虑室外实例之间的显着差异，因此缺乏实例级模型所能提供的灵活性和功能。我们通过制定和解决本地更新问题，即如何预测初始3D Cuboid猜测来构建实例级模型。我们证明了解决此问题的方法如何补充（i）构建粗到十个多分辨率系统，（ii）执行模型 - 不合命斯剂对象的位置的细化以及（iii）进行立体3D跟踪逐个检测的方法。广泛的实验证明了我们的方法的有效性，该方法在Kitti基准测试中实现了最先进的性能。代码和预训练模型可在https://github.com/nicholasli1995/snvc上获得。
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.
