AI Paper Atlas

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

Towards Generalization Across Depth for Monocular 3D Object Detection

Andrea Simonelli, Samuel Rota Buló, Lorenzo Porzi, Elisa Ricci, Peter Kontschieder

ECCV 2020 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 73 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 virtual views to MonoDIS (ablation)MonoDIS · KITTI3D val, Car 3DAP Moderate: 7.60 -> 10.89Improved
add bin-based distance estimation (5m bins) to MonoDIS (ablation)MonoDIS · KITTI3D val, Car 3DAP Moderate: 7.60 -> 5.34Hurt
add bin-based distance estimation (10m bins) to MonoDIS (ablation)MonoDIS · KITTI3D val, Car 3DAP Moderate: 7.60 -> 8.36Improved
use virtual views instead of bin-based estimation in MonoDIS (ablation)MonoDIS · KITTI3D val, Car 3DAP Moderate: 8.36 -> 10.89Improved
use virtual views instead of bin-based estimation (Cyclist) (ablation)MonoDIS · KITTI3D val, Cyclist 3DAP Moderate: 1.80 -> 1.07Hurt
reduce depth resolution Zres from 10m to 5m (ablation)MoVi-3D · KITTI3D val, Car 3DAP Moderate: 9.54 -> 11.13Improved
reduce depth resolution Zres from 20m to 10m (ablation)MoVi-3D · KITTI3D val, Car 3DAP Moderate: 6.18 -> 9.54Improved
reduce depth resolution Zres from 10m to 5m (ablation)MoVi-3D · KITTI3D val, Pedestrian 3DAP Moderate: 1.27 -> 5.52Improved
reduce depth resolution Zres from 20m to 10m (ablation)MoVi-3D · KITTI3D val, Cyclist 3DAP Moderate: 0.10 -> 0.51Improved
add virtual views (MoVi-3D vs MonoDIS), train far / val near (ablation)MonoDIS · KITTI3D Car, train far / val near3D AP Moderate: 0.1 -> 1.9Improved
add virtual views (MoVi-3D vs MonoDIS), train near / val far (ablation)MonoDIS · KITTI3D Car, train near / val far3D AP Moderate: 0.1 -> 1.4Improved
add virtual views (MoVi-3D vs MonoDIS), train near+far / val middle (ablation)MonoDIS · KITTI3D Car, train near+far / val middle3D AP Moderate: 0.4 -> 10.6Improved

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