AI Paper Atlas

Research map / 3D vision / Depth and stereo

LocalBins: Improving Depth Estimation by Learning Local Distributions

Shariq Farooq Bhat, Ibraheem Alhashim, Peter Wonka

ECCV 2022 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 141 citations (OpenAlex)

Read the paper

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 the LocalBins module to the encoder-decoder (ablation)base encoder-decoder · NYU-Depth V2 test (ablation)REL: 0.111 -> 0.106Improved
add Query-Response training with Chamfer loss (ablation)LocalBins module · NYU-Depth V2 test (ablation)REL: 0.106 -> 0.099Improved
add Query-Response training instead of naive 5x5 training (ablation)LocalBins · NYU-Depth V2 test (ablation)REL: 0.107 -> 0.099Improved
add foveated weighting in Chamfer loss (ablation)LocalBins · NYU-Depth V2 test (ablation)RMS: 0.364 -> 0.357Improved
add foveated weighting in Chamfer loss (ablation)LocalBins · NYU-Depth V2 test (ablation)REL: 0.099 -> 0.099No clear effect
use naive training with larger box 3x3 to 15x15 (ablation)LocalBins · NYU-Depth V2 test (ablation)REL: 0.108, 0.107, 0.108No clear effect
use Query-Response with 1000 queries instead of 8192 naive points (ablation)LocalBins · NYU-Depth V2 test (ablation)REL: 0.1071 -> 0.0992Improved
use sigmoid splitter instead of constant splitter (ablation)LocalBins · NYU-Depth V2 test (ablation)REL: 0.117 -> 0.100Improved
use linear norm splitter instead of sigmoid splitter (ablation)LocalBins · NYU-Depth V2 test (ablation)REL: 0.100 -> 0.099No clear effect
replace AdaBins with LocalBins (same backbone)EfficientNet-B5 · NYU-Depth V2 testREL: 0.103 -> 0.099Improved
replace AdaBins with LocalBins zero-shotEfficientNet-B5 · iBims-1 (zero-shot from NYU)REL: 0.159 -> 0.156Improved
replace AdaBins with LocalBins zero-shotEfficientNet-B5 · SUN-RGBD (zero-shot from NYU)RMS: 0.90 -> 0.88Improved

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