AI Paper Atlas

Research map / Point clouds / Point cloud classification

Point Transformer

Hengshuang Zhao, Li Jiang, Jiaya Jia, Philip H.S. Torr, Vladlen Koltun

ICCV 2021 · Point clouds › Point cloud classification · approach: Efficient point sampling architectures · 3,038 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 vector attention instead of scalar attention (ablation)Point Transformer · S3DIS Area 5mIoU: 64.6 -> 70.4Improved
use attention instead of pointwise MLP with max pooling (ablation)Point Transformer · S3DIS Area 5mIoU: 63.7 -> 70.4Improved
use relative position encoding instead of none (ablation)Point Transformer · S3DIS Area 5mIoU: 64.6 -> 70.4Improved
use relative instead of absolute position encoding (ablation)Point Transformer · S3DIS Area 5mIoU: 66.5 -> 70.4Improved
add relative position encoding to both attention and feature branches instead of only attention (ablation)Point Transformer · S3DIS Area 5mIoU: 67.0 -> 70.4Improved
add relative position encoding to both branches instead of only feature branch (ablation)Point Transformer · S3DIS Area 5mIoU: 68.7 -> 70.4Improved
add softmax normalization (ablation)Point Transformer · S3DIS Area 5mIoU: 66.5 -> 70.4Improved
use k=16 instead of k=4 neighbors (ablation)Point Transformer · S3DIS Area 5mIoU: 59.6 -> 70.4Improved
use k=16 instead of k=8 neighbors (ablation)Point Transformer · S3DIS Area 5mIoU: 67.7 -> 70.4Improved
use k=16 instead of larger k=32 (ablation)Point Transformer · S3DIS Area 5mIoU: 68.3 -> 70.4Improved
use k=16 instead of k=64 (ablation)Point Transformer · S3DIS Area 5mIoU: 67.7 -> 70.4Improved
use scalar attention instead of pointwise MLP (ablation)Point Transformer · S3DIS Area 5mIoU: 61.7 -> 64.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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