论文标题
Sparsedet：朝向端到端3D对象检测
SparseDet: Towards End-to-End 3D Object Detection
论文作者
论文摘要
在本文中，我们提出了从点云的端到端3D对象检测的Sparsedet。 3D对象检测上的现有作品依赖于在2D图像中用于对象检测的主流方法，在3D或2D网格中所有位置上的密集对象候选。但是，这种密集的范式需要数据方面的专业知识，以满足标签和检测之间的差距。作为新的检测范式，Sparsedet维护了一组固定的可学习建议，以代表潜在的候选者，并直接通过堆叠的变压器对3D对象进行分类和本地化。它表明，没有任何后处理（例如冗余去除和非最大抑制）可以实现有效的3D对象检测。通过设计正确的网络，Sparsedet以34.5 fps的效率更高的速度运行，达到了竞争激烈的检测准确性。我们认为，Sparsedet的这种端到端范式会激发人们对3D对象检测的稀疏性的新思维。
In this paper, we propose SparseDet for end-to-end 3D object detection from point cloud. Existing works on 3D object detection rely on dense object candidates over all locations in a 3D or 2D grid following the mainstream methods for object detection in 2D images. However, this dense paradigm requires expertise in data to fulfill the gap between label and detection. As a new detection paradigm, SparseDet maintains a fixed set of learnable proposals to represent latent candidates and directly perform classification and localization for 3D objects through stacked transformers. It demonstrates that effective 3D object detection can be achieved with none of post-processing such as redundant removal and non-maximum suppression. With a properly designed network, SparseDet achieves highly competitive detection accuracy while running with a more efficient speed of 34.5 FPS. We believe this end-to-end paradigm of SparseDet will inspire new thinking on the sparsity of 3D object detection.
