Papers › Confidence Propagation through CNNs for Guided Sparse Depth Regression

Confidence Propagation through CNNs for Guided Sparse Depth Regression

5 Nov 2018arXiv:1811.01791archive 2025-07-28

Abdelrahman Eldesokey, Michael Felsberg, Fahad Shahbaz Khan

Generally, convolutional neural networks (CNNs) process data on a regular grid, e.g. data generated by ordinary cameras. Designing CNNs for sparse and irregularly spaced input data is still an open research problem with numerous applications in autonomous driving, robotics, and surveillance. In this paper, we propose an algebraically-constrained normalized convolution layer for CNNs with highly sparse input that has a smaller number of network parameters compared to related work. We propose novel strategies for determining the confidence from the convolution operation and propagating it to consecutive layers. We also propose an objective function that simultaneously minimizes the data error while maximizing the output confidence. To integrate structural information, we also investigate fusion strategies to combine depth and RGB information in our normalized convolution network framework. In addition, we introduce the use of output confidence as an auxiliary information to improve the results. The capabilities of our normalized convolution network framework are demonstrated for the problem of scene depth completion. Comprehensive experiments are performed on the KITTI-Depth and the NYU-Depth-v2 datasets. The results clearly demonstrate that the proposed approach achieves superior performance while requiring only about 1-5% of the number of parameters compared to the state-of-the-art methods.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

abdo-eldesokey/nconv officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous DrivingDepth Completionregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Depth Completion KITTI Depth Completion NConv-CNN-L2 MAE 233 #7 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN-L2 RMSE 830 #7 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN-L2 Runtime [ms] 20 #7 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN-L1 MAE 208 #8 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN-L1 RMSE 859 #8 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN-L1 Runtime [ms] 20 #8 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN MAE 360 #15 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN RMSE 1268 #15 of 16 Archive leaderboard report
Depth Completion KITTI Depth Completion NConv-CNN Runtime [ms] 10 #15 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections