AI Paper Atlas

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

SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection

Yifan Wang, Yian Zhao, Fanqi Pu, Xiaochen Yang, Yang Tang, Xi Chen, Wenming Yang

CVPR 2026 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 1 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
add Spatial Point Alignment loss alone, without HTL (ablation)MonoDGP · KITTI val CarAP3D R40 Mod.: 22.34 -> 21.92Hurt
add 3D-2D Projection Alignment loss alone, without HTL (ablation)MonoDGP · KITTI val CarAP3D R40 Mod.: 22.34 -> 21.80Hurt
add Hierarchical Task Learning alone (ablation)MonoDGP · KITTI val CarAP3D R40 Mod.: 22.34 -> 22.56Improved
add HTL schedule to both SPAN losses (ablation)MonoDGP + SPAN · KITTI val CarAP3D R40 Mod.: 21.85 -> 23.26Improved
use HTL instead of linear weight schedule (ablation)MonoDGP + SPAN · KITTI val CarAP3D R40 Mod.: 22.95 -> 23.26Improved
use MGIoU instead of L1 for corner loss (ablation)MonoDGP + HTL · KITTI val CarAP3D R40 Mod.: 22.68 -> 22.89Improved
use MGIoU instead of exact 3D IoU for corner loss (ablation)MonoDGP + HTL · KITTI val CarAP3D R40 Mod.: 22.75 -> 22.89Improved
add Spatial Point Alignment to projection loss with HTL (ablation)MonoDGP · KITTI val CarAP3D R40 Mod.: 22.97 -> 23.26Improved
add 3D-2D Projection Alignment to corner loss with HTL (ablation)MonoDGP · KITTI val CarAP3D R40 Mod.: 22.89 -> 23.26Improved
raise loss weights from 0.5 to 1.0 (ablation)MonoDGP + SPAN · KITTI val CarAP3D R40 Mod.: 22.81 -> 23.26Improved
raise loss weights from 1.0 to 2.0 (ablation)MonoDGP + SPAN · KITTI val CarAP3D R40 Mod.: 23.26 -> 22.66Hurt
add 15px uniform noise to 2D boxes during training (ablation)MonoDGP + SPAN · KITTI val CarAP3D R40 Mod.: 23.26 -> 13.51Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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