AI Paper Atlas

Research map / Point clouds / Point cloud classification

RISurConv: Rotation Invariant Surface Attention-Augmented Convolutions for 3D Point Cloud Classification and Segmentation

Zhiyuan Zhang, Licheng Yang, Zhiyu Xiang

ECCV 2024 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 15 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 distance and triangle-relation features phi1-5 on top of normal angles (ablation)RISurConv · ModelNet40overall accuracy (%): 90.9 -> 96.0Improved
add normal-based tangent-space angle features (ablation)RISurConv · ModelNet40overall accuracy (%): 88.2 -> 96.0Improved
add distance L0 feature (ablation)RISurConv · ModelNet40overall accuracy (%): 95.5 -> 96.0Improved
add extra normal-angle features lambda and mu to RISP (ablation)RISurConv · ModelNet40overall accuracy (%): 96.0 -> 95.7No clear effect
add both self-attention layers and transformer encoder (ablation)RISurConv · ModelNet40overall accuracy (%): 92.8 -> 96.0Improved
add transformer encoder before FC layers (ablation)RISurConv · ModelNet40overall accuracy (%): 94.3 -> 96.0Improved
add SA1 in RISurConv (ablation)RISurConv · ModelNet40overall accuracy (%): 95.6 -> 96.0Improved
use 2 local triangle surfaces instead of 1 (ablation)RISurConv · ModelNet40overall accuracy (%): 94.7 -> 96.0Improved
use 3 or 4 local triangle surfaces instead of 2 (ablation)RISurConv · ModelNet40overall accuracy (%): 96.0 -> 91.9 (3), 89.8 (4)Hurt
rotation-invariant RISurConv vs non-invariant Point Transformer v2 under z/zRISurConv · ModelNet40 (z/z)overall accuracy (%): 94.2 -> 96.0Improved
remove transformer components to cut parameters (ablation)RISurConv · ModelNet40parameters: 13.96M -> 1.35MImproved

Later papers that compared with this method

2 later accepted papers report RISurConv as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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