AI Paper Atlas

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

Task-Aware Monocular Depth Estimation for 3D Object Detection

Xinlong Wang, Wei Yin, Tao Kong, Yuning Jiang, Lei Li, Chunhua Shen

AAAI 2020 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 75 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
Use ForeSeE instead of DenseDepthKOD depth estimation · KOD foregroundabsRel: 0.135 -> 0.118Improved
Use ForeSeE instead of DenseDepthKOD depth estimation · KOD globalabsRel: 0.138 -> 0.138No clear effect
Use ForeSeE-generated pseudo-LiDAR instead of baseline pseudo-LiDARAVOD · KITTI car easyAP3D: 7.5 -> 15.0Improved
Use ForeSeE-generated pseudo-LiDAR instead of baseline pseudo-LiDARAVOD · KITTI car moderateAP3D: 6.1 -> 12.5Improved
Use ForeSeE-generated pseudo-LiDAR instead of baseline pseudo-LiDARAVOD · KITTI car hardAP3D: 5.4 -> 12.0Improved
Add foreground-background sensitive loss (ablation)ForeSeE with separate decoders and objectives · KOD foregroundabsRel: 0.120 -> 0.118Improved
Add foreground-background sensitive loss (ablation)ForeSeE with separate decoders and objectives · KOD backgroundabsRel: 0.141 -> 0.141No clear effect
Add separate decoders while retaining separate objectives (ablation)ForeSeE · KOD backgroundabsRel: 0.147 -> 0.141Improved
Add separate decoders while retaining separate objectives (ablation)ForeSeE · KOD foregroundabsRel: 0.120 -> 0.120No clear effect
Use separate foreground and background objectives instead of one shared objective (ablation)Baseline depth estimator · KOD foregroundabsRel: 0.129 -> 0.120Improved
Use separate foreground and background objectives instead of one shared objective (ablation)Baseline depth estimator · KOD backgroundabsRel: 0.143 -> 0.147Hurt
Replace mask-based merging with mask-free element-wise maximum merging (ablation)ForeSeE inference · KODabsRel: 0.117 -> 0.118Hurt

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