AI Paper Atlas

Research map / 3D vision / 3D generation

Unifying 3D Vision-Language Understanding via Promptable Queries

ziyu zhu, Zhuofan Zhang, Xiaojian Ma, Xuesong Niu, Yixin Chen, Baoxiong Jia, Zhidong Deng, Siyuan Huang, Qing Li

ECCV 2024 · 3D vision › 3D generation · approach: Semantic scene completion · 37 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 point features to voxel features (ablation)PQ3D · ScanRefer / SQA3D / Scan2Capacc / acc / CIDEr: +3.1%, +1.7%, +6.8%Improved
add image features to voxel and point features (ablation)PQ3D · ScanRefer / SQA3D / Scan2Capacc / acc / CIDEr: +2.0%, +1.7%, +5.7%Improved
joint multi-task training instead of single-dataset training (ablation)PQ3D · Scan2CapCIDEr@0.5: 75.6 -> 80.3Improved
joint multi-task training instead of single-dataset training (ablation)PQ3D · ScanReferacc@0.5: 47.4 -> 51.2Improved
joint training on Multi3DRefer only vs unified training (ablation)PQ3D · Multi3DReferZT F1: ZT 61.1 vs 57.7; avg 48.6 vs 50.1Mixed
use a 4-layer query decoder rather than 2 or 6 layers (ablation)PQ3D · ScanReferacc@0.5: 50.2 (2-layer), 50.7 (6-layer) -> 51.2Improved
use the proposed decoder instead of sequential cross-attention (ablation)PQ3D · Nr3Daccuracy (overall): 56.1 -> 66.7Improved
add Refer task data to joint training (ablation)PQ3D · QA / Captiongain: +1.8% QA, +2.2% captionImproved
add QA task data to joint training (ablation)PQ3D · Referaccuracy: +0.0No clear effect
train with random feature dropout, infer without image features (ablation)PQ3D · ScanRefer / SQA3D / Scan2Capacc / acc / CIDEr: ScanRefer 49.2 -> 49.4No clear effect
use closed-vocabulary classification head instead of prompted CLIP textPQ3D · ScanNet200 valAP: 20.2 -> 27.0Improved
3D PQ3D features for navigation agent versus baseline VC-1VC-1 (ViT-B) · ObjNav CortexBenchsuccess rate: 57.1 -> 80.0Improved

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