AI Paper Atlas

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

Towards Intrinsic-Aware Monocular 3D Object Detection

Zhihao Zhang, Abhinav Kumar, Xiaoming Liu

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 intrinsic-aware modeling (MonoIA) instead of MonoCoP at unseen focal 1400 pxMonoCoP · KITTI Val, unseen focalsAP3D: 11.11 -> 16.99Improved
add intrinsic-aware modeling at perturbed focal +-15 pxMonoCoP · KITTI Val intrinsic mismatchAP3D: 15.42 -> 18.98Improved
add MonoIA to MonoCoP on KITTI testMonoCoP · KITTI Test Car IoU 0.7AP3D Moderate: 19.11 -> 20.29Improved
add MonoIA to MonoCoP on nuScenesMonoCoP · nuScenes ValAP3D Easy: 10.85 -> 12.33Improved
add intrinsic awareness for joint KITTI+nuScenes trainingMonoCoP · Multi-dataset, KITTIAP3D: 17.26 -> 26.54Improved
add Waymo to multi-dataset trainingMonoIA · Multi-dataset, KITTIAP3D: 26.54 -> 28.91Improved
add virtual-depth normalization to multi-dataset MonoCoPMonoCoP · Multi-dataset, KITTIAP3D: 17.26 -> 23.15Mixed
train baseline on synthetic multi-focal images without intrinsic modeling (ablation)MonoCoP · KITTI Val ablation, IoU 0.7 ModerateAP3D: 23.64 -> 21.71Hurt
add semantic Intrinsic Encoder instead of linear layer on raw intrinsics (ablation)MonoIA · KITTI Val ablation, IoU 0.7 ModerateAP3D: 22.16 -> 24.40Improved
freeze intrinsic embeddings (ablation)MonoIA · KITTI Val ablation, IoU 0.7 ModerateAP3D: 21.85 -> 24.40Improved
add Connector (ablation)MonoIA · KITTI Val ablation, IoU 0.7 ModerateAP3D: 22.85 -> 24.40Improved
add Feature-Level Adaptation (ablation)MonoIA · KITTI Val ablation, IoU 0.7 ModerateAP3D: 23.43 -> 24.40Improved

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