AI Paper Atlas

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

Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation

Yingjie Cai, Buyu Li, Zeyu Jiao, Hongsheng Li, Xingyu Zeng, Xiaogang Wang

AAAI 2020 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 86 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
decompose detection into structured polygon prediction and depth recovery rather than jointly regress all box variables (ablation)Decoupled-3D · KITTI validation, moderate, IoU=0.5AP_BEV: 12.05 -> 54.31Improved
decompose detection into structured polygon prediction and depth recovery rather than jointly regress all box variables (ablation)Decoupled-3D · KITTI validation, moderate, IoU=0.5AP_3D: 4.50 -> 50.50Improved
use structured polygon instead of BEV features to estimate coarse boxes (ablation)Decoupled-3D · KITTI validation, moderate, IoU=0.5AP_BEV: 38.61 -> 54.31Improved
use structured polygon instead of BEV features to estimate coarse boxes (ablation)Decoupled-3D · KITTI validation, moderate, IoU=0.5AP_3D: 27.88 -> 50.50Improved
use object-height-guided depth recovery instead of direct depth regression (ablation)Decoupled-3D · KITTI validationmean depth error: 2.41m -> 1.21mImproved
add fine-grained refinement using bird's-eye-view spatial features (ablation)Decoupled-3D coarse boxes · KITTI validation, moderate, IoU=0.5AP_3D: 16.36 -> 50.50Improved
refine coarse boxes with image-level features (ablation)Decoupled-3D coarse boxes · KITTI validation, moderate, IoU=0.5AP_3D: 16.36 -> 16.95Improved
refine coarse boxes with front-view depth map (ablation)Decoupled-3D coarse boxes · KITTI validation, moderate, IoU=0.5AP_3D: 16.36 -> 16.93Improved
refine coarse boxes with image-level features (ablation)Decoupled-3D coarse boxes · KITTI validation, moderate, IoU=0.5AP_BEV: 20.91 -> 20.74No clear effect
refine coarse boxes with front-view depth map (ablation)Decoupled-3D coarse boxes · KITTI validation, moderate, IoU=0.5AP_BEV: 20.91 -> 20.70No clear effect
add fine-grained refinement to Mono3D (ablation)Mono3D · KITTI validation, moderate, IoU=0.5AP_3D: 18.20 -> 29.05Improved
add fine-grained refinement to MGR (ablation)MGR · KITTI validation, moderate, IoU=0.5AP_3D: 36.97 -> 43.80Improved

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