AI Paper Atlas

Research map / Point clouds / Point cloud classification

Cloud Transformers: A Universal Approach to Point Cloud Processing Tasks

Kirill Mazur, Victor Lempitsky

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
use element-wise max instead of sum aggregation in rasterization (ablation)Cloud Transformer · S3DIS Area-5mIoU: 57.9 -> 63.7Improved
use element-wise max instead of mean aggregation (ablation)Cloud Transformer · S3DIS Area-5mIoU: 61.3 -> 63.7Improved
use element-wise max instead of sum aggregation (ablation)Cloud Transformer · ScanObjectNNaccuracy: 82.1 -> 85.0Improved
predict keys with a learned deep residual instead of linear layer (ablation)Cloud Transformer · S3DIS Area-5mIoU: 62.5 -> 63.7Improved
predict keys with a learned deep residual instead of linear layer (ablation)Cloud Transformer · ScanObjectNNaccuracy: 81.9 -> 85.0Improved
learn the key projection instead of fixed random rotation (ablation)Cloud Transformer · ScanObjectNNaccuracy: 84.9 -> 85.0No clear effect
learn the key projection instead of fixed random rotation (ablation)Cloud Transformer · S3DIS Area-5mIoU: 62.5 -> 63.7Improved
add planar heads alongside volumetric heads (ablation)Cloud Transformer · S3DIS Area-5mIoU: 63.4 -> 63.7Improved
use 16 heads instead of a single wide head (ablation)Cloud Transformer · S3DIS Area-5mIoU: 63.1 -> 63.7Improved
use full-resolution rather than coarser feature maps (ablation)Cloud Transformer · S3DIS Area-5mIoU: 62.2 -> 63.7Improved
use four CMHCT blocks instead of two (ablation)Cloud Transformer · S3DIS Area-5mIoU: 62.2 -> 63.7Improved
use eight CMHCT blocks instead of four (ablation)Cloud Transformer · S3DIS Area-5mIoU: 63.7 -> 64.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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