atlas

Research map / Detection and segmentation / 3D detection and driving

Triangulation Learning Network: From Monocular to Stereo 3D Object Detection

CVPR 2019 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 151 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 stereo TLNet to the monocular baselineOurs (baseline) · KITTI val Car Moderate, AP3D IoU=0.5AP3D: 33.98 -> 43.71Helped
replace channel reweighting with concatenation (ablation)TLNet · KITTI val Car Moderate, AP3D IoU=0.3AP3D: 63.36 -> 60.81Hurt
replace channel reweighting with element-wise addition (ablation)TLNet · KITTI val Car Moderate, AP3D IoU=0.3AP3D: 63.36 -> 59.89Hurt
replace channel reweighting with concatenation (ablation)TLNet · KITTI val Car Moderate, AP3D IoU=0.5AP3D: 43.71 -> 41.20Hurt
replace channel reweighting with element-wise addition (ablation)TLNet · KITTI val Car Moderate, AP3D IoU=0.5AP3D: 43.71 -> 41.61Hurt
replace channel reweighting with concatenation (ablation)TLNet · KITTI val Car Moderate, AP3D IoU=0.7AP3D: 14.26 -> 11.63Hurt
replace channel reweighting with element-wise addition (ablation)TLNet · KITTI val Car Moderate, AP3D IoU=0.7AP3D: 14.26 -> 13.59Hurt

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