TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK	REMOVE
Stereo-LiDAR Fusion	KITTI Depth Completion Validation	GCNet	RMSE	1031.4	# 9

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/end-to-end-learning-of-geometry-and-context/stereo-lidar-fusion-on-kitti-depth-completion)](https://paperswithcode.com/sota/stereo-lidar-fusion-on-kitti-depth-completion?p=end-to-end-learning-of-geometry-and-context)`

End-to-End Learning of Geometry and Context for Deep Stereo Regression

ICCV 2017 · Alex Kendall, Hayk Martirosyan, Saumitro Dasgupta, Peter Henry, Ryan Kennedy, Abraham Bachrach, Adam Bry ·

We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem's geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Disparity values are regressed from the cost volume using a proposed differentiable soft argmin operation, which allows us to train our method end-to-end to sub-pixel accuracy without any additional post-processing or regularization. We evaluate our method on the Scene Flow and KITTI datasets and on KITTI we set a new state-of-the-art benchmark, while being significantly faster than competing approaches.