AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds From Multiple Angles by Joint Self-Reconstruction and Half-to-Half Prediction

Zhizhong Han, Xiyang Wang, Yu-Shen Liu, Matthias Zwicker

ICCV 2019 · Point clouds › Shape and surface completion · approach: Structure-guided completion · 129 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 self-reconstruction branch R (ablation)MAP-VAE · ModelNet10 (ablation, linear SVM)accuracy (%): 91.63 -> 94.82Improved
add half-to-half prediction branch P (ablation)MAP-VAE · ModelNet10 (ablation, linear SVM)accuracy (%): 92.40 -> 94.82Improved
add KL variational constraint (ablation)MAP-VAE · ModelNet10 (ablation, linear SVM)accuracy (%): 93.17 -> 94.82Improved
add half-to-half prediction to global-encoder VAE (ablation)VAE · ModelNet10 (ablation, linear SVM)accuracy (%): 93.28 -> 94.82Improved
add half-to-half prediction to global-encoder AE (ablation)AE · ModelNet10 (ablation, linear SVM)accuracy (%): 92.29 -> 94.82Improved
use geodesic instead of Euclidean distance for splitting (ablation)MAP-VAE · ModelNet10 (ablation, linear SVM)accuracy (%): 93.61 -> 94.82Improved
increase beta from 10 to 1000 (ablation)MAP-VAE · ModelNet10 (parameter sweep)accuracy (%): 93.72 -> 94.82Improved
increase beta from 1000 to 10000 (ablation)MAP-VAE · ModelNet10 (parameter sweep)accuracy (%): 94.82 -> 93.72Hurt
use W=6 angles instead of 12 (ablation)MAP-VAE · ModelNet10 (parameter sweep)accuracy (%): 93.17 -> 94.82Improved
use W=6 angles instead of 1 (ablation)MAP-VAE · ModelNet10 (parameter sweep)accuracy (%): 92.95 -> 94.82Improved
place 6 angles uniformly instead of continuously (S-6) (ablation)MAP-VAE · ModelNet10 (parameter sweep)accuracy (%): 93.39 -> 94.82Improved
use alpha 0.01 instead of 0.1 (ablation)MAP-VAE · ModelNet10 (parameter sweep)accuracy (%): 92.62 -> 94.82Improved

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