TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Depth Completion	KITTI Depth Completion	Spade-sD	RMSE	1035	# 11
Depth Completion	KITTI Depth Completion	Spade-sD	MAE	248	# 8
Depth Completion	KITTI Depth Completion	Spade-sD	Runtime [ms]	40	# 9
Depth Completion	KITTI Depth Completion	Spade-RGBsD	RMSE	918	# 9
Depth Completion	KITTI Depth Completion	Spade-RGBsD	MAE	235	# 7
Depth Completion	KITTI Depth Completion	Spade-RGBsD	Runtime [ms]	70	# 10

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sparse-and-dense-data-with-cnns-depth/depth-completion-on-kitti-depth-completion)](https://paperswithcode.com/sota/depth-completion-on-kitti-depth-completion?p=sparse-and-dense-data-with-cnns-depth)`

Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation

2 Aug 2018 · Maximilian Jaritz, Raoul de Charette, Emilie Wirbel, Xavier Perrotton, Fawzi Nashashibi ·

Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.). We present a method to handle sparse depth data with optional dense RGB, and accomplish depth completion and semantic segmentation changing only the last layer. Our proposal efficiently learns sparse features without the need of an additional validity mask. We show how to ensure network robustness to varying input sparsities. Our method even works with densities as low as 0.8% (8 layer lidar), and outperforms all published state-of-the-art on the Kitti depth completion benchmark.

PDF Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Depth Completion

Semantic Segmentation

Datasets

Cityscapes

SYNTHIA

Results from the Paper

Edit

Ranked #9 on Depth Completion on KITTI Depth Completion

Get a GitHub badge

Results from Other Papers

Task	Dataset	Model	Metric Name	Metric Value	Rank	Compare
Depth Completion	KITTI Depth Completion	Spade-sD	RMSE	1035	# 11	See all
			MAE	248	# 8	See all
			Runtime [ms]	40	# 9	See all
Depth Completion	KITTI Depth Completion	Spade-RGBsD	RMSE	918	# 9	See all
			MAE	235	# 7	See all
			Runtime [ms]	70	# 10	See all

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Sparse and Dense Data with CNNs: Depth Completion and Semantic Segmentation

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit