AI Paper Atlas

Research map / 3D vision / Depth and stereo

Estimating Depth from RGB and Sparse Sensing

Zhao Chen, Vijay Badrinarayanan, Gilad Drozdov, Andrew Rabinovich

ECCV 2018 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 117 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
add sparse depth input (0.18% points) to the depth network (ablation)D3 · NYUv2 valRMSE (m): 0.711 -> 0.118Improved
add distance map S2 to the sparse input parametrization (ablation)D3 · validation L2 loss, random sparsity schedulerelative L2 validation loss: 34.4% improvementImproved
add distance map S2 under slow-decay schedule (ablation)D3 · validation L2 lossrelative L2 validation loss: 8.8% improvementImproved
add distance map S2 under static schedule (ablation)D3 · validation L2 lossrelative L2 validation loss: 2.8% improvementImproved
use nearest-neighbor fill of sparse depth instead of raw sparse map (ablation)D3 · NYUv2, 0.18% sparsity, standard scheduleRMSE (m): 0.287 -> 0.118Improved
use nearest-neighbor fill of sparse depth instead of raw sparse map (ablation)D3 · NYUv2, 0.18% sparsity, random scheduleRMSE (m): 0.344 -> 0.125Improved
feed S1 into every DenseNet module (ablation)D3 · NYUv2, standard scheduleRMSE (m): 0.120 -> 0.118No clear effect
feed S1 into every DenseNet module (ablation)D3 · NYUv2, random scheduleRMSE (m): 0.135 -> 0.125Improved
use slow-decay sparsity schedule instead of static pattern (ablation)D3 · training L2 loss and MRErelative decrease in loss and MRE: ~3%Improved
train jointly on NYUv2 and KITTI (mixed)D3 · NYUv2 0.18% sparsityRMSE (m): 0.118 -> 0.131Hurt
train jointly on NYUv2 and KITTI (mixed)D3 · KITTI 0.174%RMSE (m): 1.387 -> 1.472Hurt
average depth over a larger patch (11px vs 1px) for sparse samplesD3 · NYUv2 0.18% sparsityRMSE (m): 0.118 -> 0.102Improved

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