AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Variational Relational Point Completion Network for Robust 3D Classification

Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang, Haiyu Zhao, Shuai Yi, Ziwei Liu

TPAMI 2023 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 25 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 the proposed PSA kernel, dual-path architecture and PSK modules (ablation)ECG baseline · MVP completion (2048 points)Chamfer distance x10^4: 6.64 -> 5.96Improved
add the proposed modules (F-score) (ablation)ECG baseline · MVP completion (2048 points)F-score@1%: 0.476 -> 0.499Improved
add relational structure learning (VRCNet vs ECG) at 16,384 pointsECG · MVP completion (16,384 points)Chamfer distance x10^4: 3.58 -> 3.06Improved
increase output resolution from 2048 to 16384 pointsVRCNet · MVP completionChamfer distance x10^4: 5.96 -> 3.12Improved
complete partial clouds with VRCNet before classification, 50% missingPointNet/DGCNN · MVP-40 classificationaccuracyImproved
complete partial clouds with PCN before DGCNN classification (25% missing)DGCNN · MVP-40 classificationAvg accuracy: 69.0 -> 59.9Hurt
increase missing ratio from 25% to 50%VRCNet · MVP-40 completionChamfer distance x10^3: 1.89 -> 2.76Hurt
replace VRCNet with PCN on real car scans in user studyVRCNet · KITTI car user studypreference score: 2.07 -> 2.87Hurt
use VRCNet on real chair scans vs PCNPCN · ScanNet chair user studypreference score: 1.60 -> 2.67Improved
partial instead of complete input to classifierPointNet and DGCNN · MVP classificationaccuracyHurt

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