AI Paper Atlas

Research map / Point clouds / Shape and surface completion

LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints

Junshu Tang, Zhijun Gong, Ran Yi, Yuan Xie, Lizhuang Ma

CVPR 2022 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 80 citations (OpenAlex)

Check 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 aligned keypoints and surface-skeleton assistance instead of direct point completionLAKe-Net · PCN testCD-L2 (×10^4), average: Snowflake 2.336; LAKe-Net 1.944Improved
use aligned keypoints and surface-skeleton assistance instead of direct point completionLAKe-Net · PCN testEMD (×10^2), average: PointTr 1.764; LAKe-Net 1.557Improved
use aligned keypoints and surface-skeleton assistance instead of direct point completionLAKe-Net · ShapeNet55 testCD-L2 (×10^3), average: GRNet 1.15; LAKe-Net 0.89Improved
use aligned keypoints and surface-skeleton assistance instead of direct point completionLAKe-Net · ShapeNet55 testEMD (×10^3), average: GRNet 28.2; LAKe-Net 31.0Hurt
add category-specific offset predictors to the keypoint detector (ablation)LAKe-Net UMKD · KeypointNet, airplane/car/chair/table/vesselmIoU: Ours-32: 73.7, 60.2, 70.5, 63.2, 62.5; Ours-32 w/o csop: 35.4, 13.2, 27.8, 23.9, 11.0Improved
increase keypoint count from 16 to 32 (ablation)LAKe-Net UMKD · KeypointNet, airplane/car/chair/table/vesselmIoU: 73.2, 58.1, 69.2, 62.5, 61.3 -> 73.7, 60.2, 70.5, 63.2, 62.5Improved
increase keypoint count from 32 to 64 (ablation)LAKe-Net UMKD · KeypointNet, airplane/car/chair/table/vesselmIoU: 73.7, 60.2, 70.5, 63.2, 62.5 -> 74.0, 62.9, 71.3, 65.4, 64.0Improved
add aligned keypoints instead of using FPS down-sampled ground-truth points (ablation)LAKe-Net completion · PCN testEMD (×10^2), average: 1.963 -> 1.557Improved
add surface-skeleton assistance (ablation)LAKe-Net completion · PCN testEMD (×10^2), average: 2.251 -> 1.557Improved
disturb 5% of detected ground-truth keypoints (ablation)LAKe-Net completion · PCN testEMD (×10^2), average: 1.557 -> 1.700Hurt
misclassify geometrically similar categories (ablation)LAKe-Net completion · PCN testEMD (×10^2), average: 1.557 -> 1.590Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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