AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Unsupervised Point Cloud Registration via Training-Time Semantic Guidance

Kezheng Xiong, Shiyun Xu, Sheng Ao, Siqi Shen, Cheng Wang, Chenglu Wen

ECCV 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
add Semantic-aware Teacher Refining (SATR) (ablation)CAESAR · KITTI/nuScenes ablationmRR: 1.7% mRR drop when removedImproved
use L_rerank instead of global L_reg inside SATR (ablation)CAESAR · KITTI/nuScenes ablationmRR: -1.5% mRR when replaced by L_regImproved
use both s_geo and s_sem in DCRM scoring (ablation)CAESAR · KITTI/nuScenes ablationregistration performanceImproved
add Reliable Label Selection (ablation)CAESAR · KITTI/nuScenes ablationtIR@1st epochImproved
add Semantic Predictive Distillation (ablation)CAESAR · KITTI/nuScenes ablationmRRImproved
use SPD instead of vanilla L1 feature mimicry (ablation)CAESAR · KITTI/nuScenes ablationmRRImproved
train with CAESAR instead of INTEGER (cross-dataset)CAESAR · KITTI to nuScenes (cross-dataset)mRR: +11.5% mRR vs INTEGERImproved
train with CAESAR instead of INTEGER (long range, cross-dataset)CAESAR · KITTI to nuScenes (cross-dataset)RR@[40,50): +6.9% in RR@[40,50)Improved
use SATR instead of full teacher adaptationCAESAR · Teacher refinement costtrainable parameters (M): 8.76 -> 0.07Improved
use unsupervised DGT-ST semantics instead of supervised segmenter (ablation)CAESAR · KITTI/nuScenesmRRMixed
add semantic anchoring (CAESAR vs INTEGER)CAESAR · nuScenes (test)mRR: 63.1 -> 79.5Improved
add semantic anchoring (CAESAR vs INTEGER)CAESAR · KITTI (test)mRR: 84.0 -> 86.5Improved

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