AI Paper Atlas

Research map / Point clouds / Segmentation and detection

xMHashSeg: Cross-modal Hash Learning for Training-free Unsupervised LiDAR Semantic Segmentation

Jialong Zhang, Yachao Zhang, Yao Wu, Jiangming Shi, Fangyong Wang, Yanyun Qu

AAAI 2026 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 0 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 Point-SANN instead of Point-NN (ablation)xMHashSeg · nuScenes Night subsetmIoU: 32.1 -> 41.7Improved
add depth-map view as bridge between 2D and 3D (ablation)xMHashSeg · nuScenes Night subsetmIoU: 36.9 -> 41.7Improved
learn unified hash code instead of k-means on concatenated features (ablation)xMHashSeg · nuScenes Night subsetmIoU: 33.9 -> 41.7Improved
set balance factor lambda to 0.25 instead of 0 (ablation)xMHashSeg · nuScenes Night subsetmIoU: 37.1 -> 41.7Improved
set balance factor lambda to 0.25 instead of 1 (ablation)xMHashSeg · nuScenes Night subsetmIoU: 37.6 -> 41.7Improved
training-free method vs best zero-shot methodxMHashSeg · nuScenes (ZSL unseen 6 classes)mIoU: 22.4 -> 24.4Improved
training-free method vs best zero-shot methodxMHashSeg · SemanticKITTI (ZSL unseen 6 classes)mIoU: 23.9 -> 24.2Improved
training-free method vs UDA methodsxMHashSeg · nuScenes (6 class), UDA/TTA comparisonmIoU: *64.0 -> 40.9Hurt
training-free inference speed vs LattexMHashSeg · SemanticKITTIseconds per scene: 2.7 s -> 1.5 s per sceneImproved

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