AI Paper Atlas

Research map / Point clouds / Segmentation and detection

From Coarse to Fine: Deep Prototype Refinement Network for Few-Shot Point Cloud Semantic Segmentation

Changshuo Wang, Weijun Li, Shuting He, Xiang Fang, Xingyu Gao, Zhonghang Liu, Prayag Tiwari, Dimitrios Kanoulas

ICML 2026 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation

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 spatial cross-correlation features (ablation)DPR module · S3DIS 2-way 1-shot S0mIoU: 47.31 -> 80.76Improved
add common subspace features (ablation)DPR module · S3DIS 2-way 1-shot S0mIoU: 78.56 -> 80.76Improved
add dual-subspace decomposition (ablation)DPR module · S3DIS 2-way 1-shot S0mIoU: 78.99 -> 80.76Improved
add distinctive subspace features (ablation)DPR module · S3DIS 2-way 1-shot S0mIoU: 79.15 -> 80.76Improved
add channel correlation loss (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 78.62 -> 78.95Improved
add inter-class diversity loss (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 78.95 -> 79.78Improved
add inter-generation diversity loss (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 79.78 -> 80.76Improved
increase refinement iterations from 1 to 3 (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 45.83 -> 80.76Improved
increase refinement iterations from 3 to 5 (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 80.76 -> 78.75Hurt
use confidence-based MoPE instead of simple majority voting (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 76.97 -> 80.76Improved
use confidence-based MoPE instead of learnable weights (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 79.43 -> 80.76Improved
increase channel threshold from 0.5 to 0.7 (ablation)DPR-Net · S3DIS 2-way 1-shot S0mIoU: 80.76 -> 77.82Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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