AI Paper Atlas

Research map / 3D vision / 3D generation

Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints

Hojun Choi, Seulbin Hwang, Dae Kim, Kisung Kim, Hyunjung Shim, Jinhan Lee

ECCV 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 0 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 pseudo-BEV labeling (PBL) from projected 3D detections (ablation)OVBEVSeg · nuScenes multi-class OVBSnovel IoU: 0.0 -> 14.0Improved
add BAGD distillation using vanilla 3DGS (no BAGS) (ablation)OVBEVSeg · nuScenes multi-class OVBSmean IoU: 17.3 -> 7.9Hurt
use BEV-aware 3DGS (BAGS) supervision with BAGD (ablation)OVBEVSeg · nuScenes multi-class OVBSmean IoU: 7.9 -> 19.3 (PBL only: 17.3)Improved
increase distillation ratio from 0 to 0.1 (ablation)OVBEVSeg · nuScenes multi-class OVBSnovel IoU: 14.0 -> 15.3Improved
use pseudo-labels from projected 3D boxes instead of 2D-OV-then-BEV liftingOVBEVSeg · nuScenes novel classes (0% GT)mIoU: 2.1 -> 15.3Improved
use OVBEVSeg with 0% novel GT vs semi-supervised baselines with GTOVBEVSeg · nuScenes novel classesmIoU: 15.3 vs Semi-BEVseg 14.6 (20% GT) and 17.0 (40% GT)Mixed
replace UNION 3D prior with F&B VLM-based prior (ablation)OVBEVSeg · nuScenes novel classesIoU: truck 19.0 -> 14.2; motorcycle 6.6 -> 7.9; cone 11.5Mixed
apply OVBEVSeg vs closed-set projection methodsOVBEVSeg · nuScenes single-class (vehicle novel)mIoU: 24.4 (PointBeV) -> 26.6Improved
BAGD-enhanced model on map classesOVBEVSeg · nuScenes map segmentationIoU: walkway 50.2 -> 51.9; crossing 46.3 -> 49.4Improved
OVBEVSeg vs closed-set methods on base class bicycle and carOVBEVSeg · nuScenes multi-class OVBSbase-class IoU: car 42.8 -> 41.8 (TaDe); bicycle 14.2 -> 12.0Mixed

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