AI Paper Atlas

Research map / Point clouds / Segmentation and detection

PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models

Minghua Liu, Yinhao Zhu, Hong Cai, Shizhong Han, Zhan Ling, Fatih Porikli, Hao Su

CVPR 2023 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 68 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 PartSLIP few-shot prompt tuning and 3D liftingPartNetE semantic segmentation · PartNetE (45 categories)category mIoU (%): 44.3 -> 59.4Improved
Use PartSLIP few-shot prompt tuning and 3D liftingPartNetE instance segmentation · PartNetE (45 categories)category mAP50 (%): 31.9 -> 44.8Improved
Add 3D bounding-box voting and grouping (ablation)GLIP zero-shot predictions · PartNetE Chaircategory mIoU (%): 50.6 -> 60.7Improved
Add 3D bounding-box voting and grouping (ablation)GLIP zero-shot predictions · PartNetE Kettlecategory mIoU (%): 7.5 -> 20.8Improved
Add 3D bounding-box voting and grouping (ablation)GLIP zero-shot predictions · PartNetE Suitcasecategory mIoU (%): 21.1 -> 40.2Improved
Add 8-shot prompt tuning (ablation)GLIP with 3D voting/grouping · PartNetE Kettlecategory mIoU (%): 20.8 -> 72.7Improved
Add multi-view feature aggregation (ablation)GLIP with 3D voting/grouping · PartNetE Suitcasecategory mIoU (%): 40.2 -> 49.1Improved
Fuse visual features early, before vision-language fusion (ablation)GLIP multi-view aggregation · PartNetE Suitcase2D detection mAP50: 65.6 -> 68.9Improved
Fuse visual features late, before the detection head (ablation)GLIP multi-view aggregation · PartNetE Suitcase2D detection mAP50: 65.6 -> 47.3Hurt
Use partial point cloud input (ablation)PartSLIP · PartNetE Chaircategory mIoU (%): 85.3 -> 84.3No clear effect
Remove texture and use grayscale input (ablation)PartSLIP · PartNetE Chaircategory mIoU (%): 85.3 -> 84.0No clear effect
Make point cloud sparse at 128×128 resolution (ablation)PartSLIP · PartNetE Chaircategory mIoU (%): 85.3 -> 82.4Hurt

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