AI Paper Atlas

Research map / Point clouds / Point cloud classification

EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding

Yanmin Wu, Xinhua Cheng, Renrui Zhang, Zesen Cheng, Jian Zhang

CVPR 2023 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 69 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 explicit text decoupling and dense alignment instead of sparse main-object-word alignmentEDA · ScanRefer OverallAcc@0.25IoU: 50.42 -> 54.59Improved
Use explicit text decoupling and dense alignment instead of sparse main-object-word alignmentEDA · SR3D and NR3DAcc@0.25IoU: 65.6 -> 68.1; 51.5 -> 52.1Improved
Add position-aligned loss to semantic-aligned loss (ablation)EDA · ScanReferAcc@0.25IoU: 52.2 -> 54.6Improved
Add semantic-aligned loss to position-aligned loss (ablation)EDA · ScanReferAcc@0.25IoU: 51.2 -> 54.6Improved
Add Attribute, Pronoun, Relationship, and Auxiliary object components to Main object alignment (ablation)EDA · ScanReferAcc@0.25IoU: 51.5 -> 54.6Improved
Add the Relationship component to Main object alignment (ablation)EDA · ScanRefer VG-w/o-ONAcc@0.25IoU: 21.8 -> 23.2Improved
Replace meaningful decoupled components with four randomly selected words (ablation)EDA · ScanReferAcc@0.25IoU: 54.6 -> 52.0Hurt
Increase the weight of Main object to 1.0 while other component weights remain 0.2 (ablation)EDA position-aligned loss · ScanReferAcc@0.25IoU: 54.6 -> 53.2Hurt
Use GT candidate boxes without retrainingEDA · ScanRefer OverallAcc@0.25IoU: 54.59 -> 57.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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