TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
3D Object Detection From Stereo Images	KITTI Cars Moderate	TL-Net	AP75	4.37	# 12

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/triangulation-learning-network-from-monocular-1/3d-object-detection-from-stereo-images-on-1)](https://paperswithcode.com/sota/3d-object-detection-from-stereo-images-on-1?p=triangulation-learning-network-from-monocular-1)`

Triangulation Learning Network: from Monocular to Stereo 3D Object Detection

CVPR 2019 · Zengyi Qin, Jinglu Wang, Yan Lu ·

In this paper, we study the problem of 3D object detection from stereo images, in which the key challenge is how to effectively utilize stereo information. Different from previous methods using pixel-level depth maps, we propose employing 3D anchors to explicitly construct object-level correspondences between the regions of interest in stereo images, from which the deep neural network learns to detect and triangulate the targeted object in 3D space. We also introduce a cost-efficient channel reweighting strategy that enhances representational features and weakens noisy signals to facilitate the learning process. All of these are flexibly integrated into a solid baseline detector that uses monocular images. We demonstrate that both the monocular baseline and the stereo triangulation learning network outperform the prior state-of-the-arts in 3D object detection and localization on the challenging KITTI dataset.