AI Paper Atlas

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

Disentangling Monocular 3D Object Detection

Andrea Simonelli, Samuel Rota Bulo, Lorenzo Porzi, Manuel Lopez-Antequera, Peter Kontschieder

ICCV 2019 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 533 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 signed IoU loss to RetinaNet (ablation)RetinaNet · KITTI3D Car 2D, ModerateAP|R40: 83.74 -> 84.05Improved
add disentanglement to signed IoU loss (ablation)RetinaNet + IoU · KITTI3D Car 2D, ModerateAP|R40: 84.05 -> 85.38Improved
replace direct 10D regression with entangled 3D box loss (ablation)Regression · KITTI3D Car 3D, ModerateAP|R40: 0.90 -> 2.70Improved
add signed IoU 2D loss and 3D confidence (ablation)3D BB · KITTI3D Car 3D, ModerateAP|R40: 2.70 -> 6.10Improved
add signed IoU 2D loss and 3D confidence (ablation)Regression · KITTI3D Car 3D, ModerateAP|R40: 0.90 -> 1.70Improved
add disentangling to the 3D box loss (ablation)3D BB · KITTI3D Car 3D, ModerateAP|R40: 2.70 -> 3.00Improved
combine all contributions (MonoDIS vs 3D BB w/ IoUDIS, 3DConf) (ablation)3D BB w/ IoUDIS, 3DConf · KITTI3D Car 3D, ModerateAP|R40: 6.10 -> 7.60Improved
rank detections by 3D confidence instead of 2D confidence (ablation)MonoDIS · KITTI3D val Car 3D, ModerateAP|R11: 4.91 -> 14.98Improved
rank detections by 3D confidence instead of random confidence (ablation)MonoDIS · KITTI3D val Car 3D, ModerateAP|R11: 2.37 -> 14.98Improved
use entangled 3D box loss vs regression, effect on 2D detection (ablation)Regression · KITTI3D Car 2D, ModerateAP|R40: 73.20 -> 77.10Improved
train on larger training splitMonoDIS · KITTI3D test Car 3D, ModerateAP|R40: 4.89 -> 7.94Improved
use disentangled loss instead of entangled in toy optimization (ablation)3D box loss · toy KITTI3D box fittingconvergenceImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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