AI Paper Atlas

Research map / Point clouds / Shape and surface completion

A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks

Sangpil Kim, Hyung-gun Chi, Xiao Hu, Qixing Huang, Karthik Ramani

ECCV 2020 · Point clouds › Shape and surface completion · approach: Unsupervised shape correspondence · 105 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
move from aligned dataset A to unaligned dataset BRotationNet · MCB retrieval, micromAP: 0.805 -> 0.607Hurt
move from aligned dataset A to unaligned dataset BVRN · MCB retrieval, micromAP: 0.653 -> 0.628Hurt
move from aligned dataset A to unaligned dataset BDLAN · MCB retrieval, micromAP: 0.879 -> 0.908Improved
move from aligned dataset A to unaligned dataset BPointNet++ · MCB classificationaccuracy over object (%): 87.45 -> 93.91Improved
move from aligned dataset A to unaligned dataset BVRN · MCB classificationaccuracy over object (%): 93.17 -> 85.44Hurt
move from ModelNet40 to mechanical components (dataset A)MVCNN · classificationaccuracy over object (%): 95.0 -> 64.67Hurt
move from ModelNet40 to mechanical components (dataset A)RotationNet · classificationaccuracy over object (%): 97.37 -> 97.35Hurt
move from ModelNet40 to mechanical components (dataset A)DLAN · classificationaccuracy over object (%): 84.0 -> 93.53Improved
add view-order correspondence estimation (RotationNet vs MVCNN)RotationNet · MCB dataset A classificationaccuracy over object (%): 64.67 -> 97.35Improved
increase point cloud density from 128 to 2,048 points (ablation)PointNet++, SpiderCNN, PointCNN · MCB dataset B classificationaccuracyImproved

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