AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Unlocking Textual and Visual Wisdom: Open-Vocabulary 3D Object Detection Enhanced by Comprehensive Guidance from Text and Image

Pengkun Jiao, Na Zhao, Jingjing Chen, Yu-Gang Jiang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 16 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 image-guided novel class discovery (IGND) (ablation)class-agnostic 3DETR · SUN RGB-DmAR novel: 34.12 -> 51.12Improved
add IGND without feature alignment (ablation)3DETR · SUN RGB-DmAP base: 4.03 -> 2.07Hurt
add instance-level 3D-image alignment (ablation)IGND detector · SUN RGB-DmAP novel: 0.35 -> 6.85Improved
add class-level cross-modal alignment (ablation)IGND + instance alignment · SUN RGB-DmAP novel: 6.85 -> 8.03Improved
add scene-level alignment (PISE) (ablation)IGND + instance + class alignment · SUN RGB-DmAP novel: 8.03 -> 8.91Improved
add image-guided query seed initialization (ablation)IGND · SUN RGB-DmAR novel: 48.31 -> 51.12Improved
add instance-level alignment on top of IGND (ablation)IGND detector · SUN RGB-DmAR novel: 51.12 -> 50.70No clear effect
use INHA instead of CoDAOV-3DDet · SUN RGB-DmAP novel: 6.71 -> 8.91Improved
use INHA instead of CoDAOV-3DDet · ScanNetv2mAP novel: 6.54 -> 7.79Improved
use INHA instead of CoDA across ScanNet-10 classesOV-3DDet · ScanNet-10per-class mAP: 28.76 -> 30.06 average; sink 45.26 -> 35.69Mixed

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