AI Paper Atlas

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

OV-SCAN: Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection

Adrian Chow, Evelien Riddell, Yimu Wang, Sean Sedwards, Krzysztof Czarnecki

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 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
use adaptive 3D box search instead of greedy search at same 150,000 iterations (ablation)OV-SCAN SC-NOD · nuScenesmAP: 25.4 -> 31.1Improved
use adaptive search with only 37,500 iterations instead of 150,000 greedy (ablation)OV-SCAN SC-NOD · nuScenesmAP: 25.4 -> 28.9Improved
increase adaptive search iterations from 37,500 to 150,000 (ablation)OV-SCAN SC-NOD · nuScenesmAP: 28.9 -> 31.1Improved
balance cost weights (5.0,1.0,1.0,3.0) instead of density-only (ablation)OV-SCAN SC-NOD · nuScenesmAP: 26.1 -> 31.1Improved
use tuned weights instead of equal weights (ablation)OV-SCAN SC-NOD · nuScenesmAP: 27.4 -> 31.1Improved
add resolution filter (threshold 4000) (ablation)OV-SCAN selective alignment · nuScenesmAP: 30.4 -> 31.1Improved
raise resolution filter threshold from 4000 to 10000 (ablation)OV-SCAN selective alignment · nuScenesmAP: 31.1 -> 30.6Hurt
add fixed occlusion filter (ablation)OV-SCAN selective alignment · nuScenesmAP: 29.4 -> 30.7Improved
use class-based occlusion thresholds instead of fixed (ablation)OV-SCAN selective alignment · nuScenesmAP: 30.7 -> 31.1Improved
add two-stage class-guided alignment to one-stage FFN (ablation)OV-SCAN alignment head · nuScenesmAP: 25.2 -> 29.4Improved
add text-prompt guided alignment (H2SA) to two-stage FFN (ablation)OV-SCAN alignment head · nuScenesmAP: 29.4 -> 31.1Improved
add camera image backbone and fine-tune (OV-SCAN-Fusion)OV-SCAN · nuScenesmAP: 31.1 -> 33.8Improved

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