AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Self-Supervised Learning of LiDAR 3D Point Clouds via 2D-3D Neural Calibration

Yifan Zhang, Junhui Hou, Siyu Ren, Jinjian Wu, Yixuan Yuan, Guangming Shi

TPAMI 2025 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 17 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 learnable transformation alignment to the baseline pretext task (ablation)NCLR pre-training · nuScenes semantic seg (1% labels, ablation split)mIoU: 35.90 -> 36.52Improved
add overlapping area detection on top of learnable transformation alignment (ablation)NCLR pre-training · nuScenes semantic seg (1% labels, ablation split)mIoU: 36.52 -> 37.13Improved
add end-to-end pose estimation (soft matching, differentiable EPnP, pose loss) (ablation)NCLR pre-training · nuScenes semantic seg (1% labels, ablation split)mIoU: 37.13 -> 37.92Improved
use learnable transformation alignment instead of plain cosine similarity (ablation)image-point feature similarity · SemanticKITTI valfeature similarity: 0.55 ± 0.17 -> 0.69 ± 0.13Improved
replace hard matching with soft matching (cosine similarity) (ablation)point-to-pixel matching · SemanticKITTI feature matchingmatching accuracy (<5 px): 69.22 -> 74.27Improved
add learnable transformation alignment (hard matching) (ablation)point-to-pixel matching · SemanticKITTI feature matchingmatching accuracy (<5 px): 69.22 -> 83.18Improved
combine learnable alignment with soft matching (ablation)point-to-pixel matching · SemanticKITTI feature matchingmatching accuracy (<5 px): 83.18 -> 90.28Improved
use NCLR pre-training instead of no pre-training with 0.1% labelsMinkUNet · nuScenes semantic segmIoU: 21.6 -> 26.6Improved
use NCLR pre-training instead of training from scratch with 0.1% labelsMinkUNet · SemanticKITTI semantic segmIoU: 30.0 -> 39.2Improved
NCLR pre-training with full labels versus no pre-trainingMinkUNet · SemanticKITTI semantic seg (100% labels)mIoU: 62.7 -> 63.9Improved
PointContrast/DepthContrast pre-training with full labelsMinkUNet · nuScenes semantic seg (100% labels)mIoU: 71.2 -> 71.1No clear effect
NCLR pre-training for detection with 10% KITTI labelsPV-RCNN · KITTI3D (10% labels)mAP: 64.04 -> 66.93Improved

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