AI Paper Atlas

Research map / 3D vision / Depth and stereo

Confidence Propagation through CNNs for Guided Sparse Depth Regression

Abdelrahman Eldesokey, Michael Felsberg, Fahad Shahbaz Khan

TPAMI 2019 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 296 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enforce non-negativity of applicability via SoftPlus(beta=10) (ablation)MS-Net[LF]-L1 (gd) · KITTI-Depth (selected val subset, 1k images)RMSE [mm]: 1042.65 -> 908.76Improved
enforce non-negativity of applicability via SoftPlus(beta=10) (ablation)MS-Net[LF]-L1 (gd) · KITTI-Depth (selected val subset, 1k images)MAE [mm]: 277.67 -> 209.56Improved
add output confidence to the RGB feature extraction network (ablation)MS-Net[LF]-L2 (gd) · KITTI-Depth (selected val subset, 1k images)RMSE [mm]: 919.55 -> 870.82Improved
add depth refinement layers (ablation)MS-Net[LF]-L2 (gd) · KITTI-Depth (selected val subset, 1k images)RMSE [mm]: 912.82 -> 870.82Improved
freeze the unguided network instead of training end-to-end (ablation)MS-Net[LF]-L2 (gd) · KITTI-Depth (selected val subset, 1k images)RMSE [mm]: 886.09 -> 870.82Improved
late fusion instead of early fusion in multi-stream networkMS-Net · KITTI-Depth (selected val subset, 1k images)RMSE [mm]: 932.01 -> 908.76Improved
early fusion instead of late fusion in encoder-decoder networkEncDec-Net · KITTI-Depth (selected val subset, 1k images)RMSE [mm]: 1053.91 -> 1007.71Improved
use normalized convolution with confidence propagation instead of doubled-depth standard CNN (ablation)EncDec-Net[EF] · KITTI-DepthRMSE [mm]: 1122.51 -> 1007.71Improved
add confidence term to the loss (versus Huber norm only) (ablation)unguided NConv-CNN · KITTI-DepthMAEImproved
train with L2 loss instead of L1 lossMS-Net[LF] (gd) · KITTI-Depth (test set)RMSE [mm]: 859.22 -> 829.98Improved
train with L1 loss instead of L2 lossMS-Net[LF] (gd) · KITTI-Depth (test set)MAE [mm]: 233.26 -> 207.77Improved
SoftPlus instead of ReLU as non-negative function (ablation)unguided NConv-CNN · KITTI-DepthconvergenceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy