AI Paper Atlas

Research map / Point clouds / Point cloud classification

InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds Through Instance Multi-Level Contextual Referring

Zhihao Yuan, Xu Yan, Yinghong Liao, Ruimao Zhang, Sheng Wang, Zhen Li, Shuguang Cui

ICCV 2021 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D · 129 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 the RP module to the AP module (ablation)InstanceRefer · ScanRefer valOverall Acc@0.5: 29.46 -> 30.49Improved
add the GLP module to AP+RP (ablation)InstanceRefer · ScanRefer valOverall Acc@0.5: 30.49 -> 31.04Improved
add the co-attention matching module over cosine-similarity ranking (ablation)InstanceRefer · ScanRefer valOverall Acc@0.5: 31.04 -> 32.93Improved
use RP instead of GLP as the single module (ablation)InstanceRefer · ScanRefer valOverall Acc@0.5: 25.29 -> 28.01Improved
use AP instead of RP as the single module (ablation)InstanceRefer · ScanRefer valOverall Acc@0.5: 28.01 -> 29.46Improved
replace ScanRefer proposals with PointGroup panoptic instancesScanRefer · ScanRefer valOverall Acc@0.5: 24.32 -> 29.07Improved
use instance point clouds instead of points in GT boxesScanRefer · ScanRefer val (GT)Overall Acc@0.5: 40.06 -> 44.48Improved
use GT language classification instead of predicted (ablation)InstanceRefer · ScanRefer valOverall Acc@0.5: 32.93 -> 33.35No clear effect
replace GRU with pre-trained BERT language encoderTGNN · ScanRefer valOverall Acc@0.5: 27.92 -> 29.70Improved
swap ScanRefer/ReferIt3DNet for InstanceRefer on PG instancesPG + ScanRefer · ScanRefer valOverall Acc@0.5: 29.07 -> 32.93Improved

Later papers that compared with this method

3 later accepted papers report InstanceRefer as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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