Papers › Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling

Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling

20 May 2022arXiv:2205.09962archive 2025-07-28

Kevin Tirta Wijaya, Dong-Hee Paek, Seung-Hyun Kong

Existing point cloud feature learning networks often incorporate sequences of sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation to learn high-semantic point features that represent the global context of a point cloud. Unfortunately, the compounded loss of information concerning granularity and non-maximum point features due to sampling and max pooling could adversely affect the high-semantic point features from existing networks such that they are insufficient to represent the local context of a point cloud, which in turn may hinder the network in distinguishing fine shapes. To cope with this problem, we propose a novel point cloud feature learning network, PointStack, using multi-resolution feature learning and learnable pooling (LP). The multi-resolution feature learning is realized by aggregating point features of various resolutions in the multiple layers, so that the final point features contain both high-semantic and high-resolution information. On the other hand, the LP is used as a generalized pooling function that calculates the weighted sum of multi-resolution point features through the attention mechanism with learnable queries, in order to extract all possible information from all available point features. Consequently, PointStack is capable of extracting high-semantic point features with minimal loss of information concerning granularity and non-maximum point features. Therefore, the final aggregated point features can effectively represent both global and local contexts of a point cloud. In addition, both the global structure and the local shape details of a point cloud can be well comprehended by the network head, which enables PointStack to advance the state-of-the-art of feature learning on point clouds. The codes are available at https://github.com/kaist-avelab/PointStack.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

LongerVision/PointStack officialmentioned on GitHubpytorch report
kaist-avelab/PointStack officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Point Cloud Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Point Cloud Classification ModelNet40 PointStack Mean Accuracy 89.6 #67 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 PointStack Overall Accuracy 93.3 #67 of 111 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointStack Mean Accuracy 86.2 #44 of 77 Archive leaderboard report
3D Point Cloud Classification ScanObjectNN PointStack Overall Accuracy 87.2 #44 of 77 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Max Pooling

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections