AI Paper Atlas

Research map / Point clouds / Point cloud classification

A Closer Look at Rotation-Invariant Deep Point Cloud Analysis

Feiran Li, Kent Fujiwara, Fumio Okura, Yasuyuki Matsushita

ICCV 2021 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 54 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 pose selector module over the 24 canonical poses (ablation)DGCNN with PCA canonical poses · ModelNet40accuracy (%): 91.3 -> 91.6Improved
add the pose selector module over the 24 canonical poses (ablation)DGCNN with PCA canonical poses · ShapeNet partmIoU (%): 82.8 -> 83.1Improved
use all 24 ambiguities (4 sign x 6 order) instead of fixing order by eigenvalue sorting (Strategy I, 4 ambiguities) (ablation)DGCNN with PCA canonical poses · ModelNet40accuracy (%): 89.5 -> 91.6Improved
use all 24 ambiguities instead of fixing signs by majority of data (Strategy II, 6 ambiguities) (ablation)DGCNN with PCA canonical poses · ModelNet40accuracy (%): 90.3 -> 91.6Improved
use all 24 ambiguities instead of eliminating all ambiguities (Strategy III) (ablation)DGCNN with PCA canonical poses · ModelNet40accuracy (%): 87.2 -> 91.6Improved
use 8 sign combinations (including improper rotations) instead of the correct ambiguities (ablation)DGCNN with PCA canonical poses · ModelNet40accuracy (%): 89.2%, 2.4% lower than with correctly identified ambiguities; worse than Strategy I (89.5)Hurt
manually pick the best of 24 poses instead of feeding all 24 poses (ablation)DGCNN with PCA canonical poses · ModelNet40accuracy (%): 91.6 -> 92.0Improved
manually pick the best of 24 poses instead of feeding all 24 poses (ablation)DGCNN with PCA canonical poses · ShapeNet partmIoU (%): 83.1 -> 84.7Improved
use manually pre-aligned pose instead of the selected PCA canonical poseDGCNN · ModelNet40accuracy (%): 92.0 -> 92.9Improved
add test-time augmentation over 24 concatenation patternspose selector DGCNN · ModelNet40accuracy (%): 90.2 -> 91.6Improved
add test-time augmentation over 24 concatenation patternspose selector DGCNN · ScanObjectNN OBJ_BGaccuracy (%): 84.3 -> 86.7Improved
use correctly identified PCA ambiguities with pose selector instead of LGR-Netreal-world rotation-invariant classification · ScanObjectNN OBJ_BGaccuracy (%): 81.4 -> 86.7 (5.3% enhancement)Improved

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