AI Paper Atlas

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

MonoSOWA: Scalable Monocular 3D Object Detector Without Human Annotations

Jan Skvrna, Lukas Neumann

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Monocular 3D object detection · 4 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 Local Object Motion Model (ablation)MonoSOWA pseudo-labels · KITTI train EasyAP_3D@0.5: 17.40 -> 29.05Improved
add Saturated Closeness Criterion (ablation)MonoSOWA pseudo-labels · KITTI train EasyAP_3D@0.5: 29.05 -> 32.29Improved
add SCC without LOMM (ablation)MonoSOWA pseudo-labels · KITTI train EasyAP_3D@0.5: 17.40 -> 17.16No clear effect
add Canonical Object Space when mixing KITTI and KITTI-360 (ablation)MonoDETR (human labels) · KITTI val EasyAP_3D@0.3: 69.62 -> 81.25Improved
naively add KITTI-360 without COS (ablation)MonoDETR (human labels) · KITTI val EasyAP_3D@0.3: 79.72 -> 69.62Hurt
add real LiDAR for pseudo-label generation (ablation)MonoSOWA · KITTI val EasyAP_3D@0.5: 51.55 -> 60.04Improved
pretrain on pseudo-labels then fine-tune on 1% Waymo human labelsMonoDETR · Waymo valAP_3D@0.5: 13.81 -> 18.43Improved
pretrain on pseudo-labels then fine-tune on 5% Waymo human labelsMonoDETR · Waymo valAP_3D@0.5: 18.12 -> 20.68Improved
pretrain on pseudo-labels, fine-tune with 15% labelsMonoDETR · Waymo valAP_3D@0.5: 20.60 -> 20.88Improved
pretrain on KITTI-360 pseudo-labels, 25% KITTI labels vs 100% human onlyMonoDETR · KITTI val EasyAP_3D@0.7: 29.36 -> 32.64Improved
increase aggregation frames beyond +-30 (ablation)MonoSOWA pseudo-labels · KITTI train EasyAP_BEV@0.5: 40.21 -> 39.23No clear effect
steepness alpha 10 vs 1 (ablation)MonoSOWA SCC · KITTI train ModerateAP_BEV@0.5: 28.28 -> 33.10Improved

Later papers that compared with this method

1 later accepted paper reports MonoSOWA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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