AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Multi3DRefer: Grounding Text Description to Multiple 3D Objects

Yiming Zhang, ZeMing Gong, Angel X. Chang

ICCV 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Visual grounding transformers · 94 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 contrastive loss between sentence and object features (ablation)M3DRef-CLIP · Nr3D val (GT boxes)accuracy All: 42.9 -> 49.4Improved
add contrastive loss (ablation)M3DRef-CLIP · Multi3DRefer val (GT boxes)F1 overall: 61.1 -> 62.3Improved
add contrastive loss (ablation)M3DRef-CLIP · ScanRefer val (GT boxes)accuracy All: 55.4 -> 56.9Improved
replace GRU+GloVe text encoder with CLIP text encoder (ablation)M3DRef-CLIP · Multi3DRefer val (GT boxes)F1 overall: 59.1 -> 61.3Improved
add CLIP image features of rendered proposals to 3D features (ablation)M3DRef-CLIP · Multi3DRefer val (GT boxes)F1 overall: 61.3 -> 62.3Improved
use CLIP image features alone instead of 3D features (ablation)M3DRef-CLIP · Multi3DRefer val (GT boxes)F1 overall: 61.3 -> 54.4Hurt
train on Multi3DRefer (ST) plus ScanRefer (ablation)M3DRef-CLIP · ScanRefer val (GT boxes)accuracy All: 56.9 -> 58.7Improved
train on Multi3DRefer (ST) data only versus ScanRefer (ablation)M3DRef-CLIP · ScanRefer val (GT boxes)accuracy All: 56.9 -> 55.0Hurt
M3DRef-CLIP versus prior methods on ScanReferM3DRef-CLIP · ScanRefer val Acc@0.5accuracy All: 40.6 -> 44.7Improved
M3DRef-CLIP on Nr3D with GT boxesM3DRef-CLIP · Nr3D valaccuracy All: 55.4 (MVT) vs 49.4Hurt
M3DRef-CLIP versus 3DJCG on zero-target handling with predicted boxesM3DRef-CLIP · Multi3DRefer ZT w/ D (pred boxes)F1@0.5: 66.9 (3DJCG) vs 39.4Hurt

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