AI Paper Atlas

Research map / Point clouds / Point cloud classification

Efficient Point Cloud Processing With High-Dimensional Positional Encoding and Non-Local MLPs

Yanmei Zou, Hongshan Yu, Yaonan Wang, Zhengeng Yang, Xieyuanli Chen, Kailun Yang, Naveed Akhtar

TPAMI 2026 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 2 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 HPE to the ABS stage only (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 63.9 -> 70.0Improved
add HPE to the REF stage only (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 63.9 -> 70.7Improved
add HPE to both ABS and REF stages (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 63.9 -> 72.2Improved
add Backward Fusion Module (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 72.2 -> 72.3No clear effect
use high-dimensional HPE instead of 3-dim PE (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 70.9 -> 72.2Improved
use default HPE instead of multiplicative HPE (mul) (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 71.0 -> 72.2Improved
use default HPE instead of absolute-coordinate variant (abs) (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 54.6 -> 72.2Improved
increase HPE_MLP dimension from 3 to C/4 (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 70.9 -> 72.2Improved
increase HPE_MLP dimension from C/4 to C (ablation)HPENet V2-XL · S3DIS Area-5mIoU: 72.2 -> 71.8Hurt
use PreConv instead of Conv in ABS stage (efficient aggregation) (ablation)Conv/Conv model · S3DIS Area-5mIoU: 66.6 -> 65.6Hurt
add positional encoding to PreConv (ablation)PreConv/PreConv · S3DIS Area-5mIoU: 58.8 -> 66.7Improved
replace PE with HPE in hybrid PreConv model (ablation)PreConv+Conv first ABS · S3DIS Area-5mIoU: 67.1 -> 68.6Improved

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