AI Paper Atlas

Research map / Point clouds / Point cloud classification

Deformation-based In-Context Learning for Point Cloud Understanding

Chengxing Lin, Jinhong Deng, Yinjie Lei, Wen Li

CVPR 2026 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 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
fully mask the query target during training to match inference (ablation)PIC-Cat · ShapeNet In-Context ablationRegistration CD: 14.1 -> 3.5Improved
fully mask the query target during training (ablation)PIC-Cat · ShapeNet In-Context ablationReconstruction CD: 4.3 -> 3.2Improved
add Deformation Transfer Network (deformation instead of masked reconstruction) (ablation)PIC-Cat + consistency · ShapeNet In-Context ablationRegistration CD: 3.5 -> 2.9Improved
add Deformation Extraction Network (ablation)PIC-Cat + DTN · ShapeNet In-Context ablationRegistration CD: 2.9 -> 2.0Improved
add Deformation Extraction Network (ablation)PIC-Cat + DTN · ShapeNet In-Context ablationDenoising CD: 3.8 -> 3.5Improved
replace masked point modeling with deformationPIC-S-Sep · ShapeNet In-ContextRegistration CD: 6.7 -> 2.0Improved
use DeformPIC instead of multitask Point-MAE out of domainPoint-MAE · ModelNet40 In-ContextRegistration CD: 38.2 -> 2.3Improved
use DeformPIC instead of specialized ACT on reconstruction L5ACT (task-specific) · ShapeNet In-Context L5Reconstruction CD: 2.8 -> 3.9Hurt
use DeformPIC instead of PIC-S-Cat on part segmentationPIC-S-Cat · ShapeNet In-ContextPart segmentation mIoU: 83.8 -> 83.9Improved
use DeformPIC instead of PIC-Cat on ScanObjectNN denoisingPIC-Cat · ScanObjectNN In-ContextDenoising CD: 9.2 -> 5.0Improved

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