AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Monocular Depth Estimation Using Neural Regression Forest

Anirban Roy, Sinisa Todorovic

CVPR 2016 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 353 citations (OpenAlex)

Check 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
use NRF instead of the strongest listed baselineMonocular depth estimation · Make3Drel: 0.307 -> 0.26Improved
use NRF instead of the strongest listed baselineMonocular depth estimation · NYUv2rel: 0.215 -> 0.187Improved
forward parent CNN outputs to child split nodes (ablation)NRF · Make3Drel: 0.312 -> 0.26Improved
forward parent CNN outputs to child split nodes (ablation)NRF · NYUv2rel: 0.24 -> 0.187Improved
add neighboring-window depth information (ablation)NRF · Make3Drel: 0.29 -> 0.26Improved
add neighboring-window depth information (ablation)NRF · NYUv2rel: .22 -> 0.187Improved

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