AI Paper Atlas

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

Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection

Zhuoling Li, Zhan Qu, Yang Zhou, Jianzhuang Liu, Haoqian Wang, Lihui Jiang

CVPR 2022 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 84 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
produce diverse depths from direct estimation, height, and keypoint geometry (ablation)MonoDDE · KITTI validation CarAP3D70 (%): 18.01 -> 19.75Improved
use depth from keypoint only instead of direct depth only (ablation)MonoDDE · KITTI validation Car ModerateAP3D70 (%): 18.01 -> 18.74Improved
combine all three depth-solving strategies rather than any two (ablation)MonoDDE · KITTI validation Car ModerateAP3D70 (%): 19.18 -> 19.75Improved
use variance-weighted combination instead of arithmetic mean (ablation)MonoDDE · KITTI validation Car ModerateAP3D70 (%): 14.31 -> 19.26Improved
add iterative outlier selection to weighted depth combination (ablation)MonoDDE · KITTI validation Car ModerateAP3D70 (%): 19.26 -> 19.75Improved
replace iterative outlier selection with minimum-variance selection (ablation)MonoDDE · KITTI validation Car ModerateAP3D70 (%): 19.75 -> 19.59Hurt
use 3D IoU to model conditional confidence instead of no conditional confidence (ablation)MonoDDE · KITTI validation Car ModerateAP3D70 (%): 18.15 -> 18.54Improved
combine depth confidence and 3D box confidence for conditional confidence (ablation)MonoDDE · KITTI validation Car ModerateAP3D70 (%): 19.48 -> 19.75Improved
use diverse depth clues rather than direct depth aloneMonoDDE · KITTI test Car ModerateAP3D70 (%): 14.17 -> 17.14Improved
use MonoDDE rather than CaDDNKITTI test Pedestrian Moderate · KITTI test Pedestrian ModerateAP3D50 (%): 8.14 -> 7.32Hurt

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