AI Paper Atlas

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

Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding

Runyu Ding, Jihan Yang, Chuhui Xue, Wenqing Zhang, Song Bai, Xiaojuan Qi

TPAMI 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary 3D and world perception · 42 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 binary calibration module (ablation)OV-SparseConvNet · ScanNet B15/N4 semantic seghIoU: 00.0 -> 39.8Improved
add scene-level, view-level or entity-level point-language supervision to binary calibration (ablation)Lowis3D · ScanNet semantic seghIoU: 39.8 -> 54.6 / 61.3 / 63.6Improved
add entity-level instead of scene-level caption supervision (ablation)Lowis3D · ScanNet B13/N4 instance seghAP50: 52.8 -> 56.6Improved
add debiased instance localization (DIL) (ablation)Lowis3D · ScanNet B13/N4 instance seghAP50: 54.9 -> 59.1Improved
add DIL (ablation)Lowis3D · ScanNet B13/N4 offset errormAE novel: 0.69 -> 0.48Improved
add DIL (ablation)Lowis3D · ScanNet B13/N4 proposalshAR: 44.7 -> 47.9Improved
add language supervision (PLA w/o Cap. vs PLA / Lowis3D) (ablation)PLA · ScanNet B15/N4 semantic seghIoU: 39.7 -> 65.3Improved
use CLIP text encoder instead of BERT (ablation)Lowis3D · ScanNet B15/N4 semantic seghIoU: 61.2 -> 65.3Improved
use CLIP text encoder instead of GPT2 (ablation)Lowis3D · ScanNet B15/N4 semantic seghIoU: 61.0 -> 65.3Improved
use OFA instead of ViT-GPT2 captioner (ablation)Lowis3D · ScanNet B10/N9 semantic seghIoU: 53.1 -> 56.6Improved
keep only label names in captions instead of full caption (ablation)Lowis3D · ScanNet B15/N4 semantic seghIoU: 65.3 -> 57.6Hurt
keep only entities instead of full caption (ablation)Lowis3D · ScanNet B15/N4 semantic seghIoU: 65.3 -> 65.7No clear effect

Later papers that compared with this method

1 later accepted paper reports Lowis3D as a baseline in their results tables; 1 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