Papers › DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion

DSPoint: Dual-scale Point Cloud Recognition with High-frequency Fusion

19 Nov 2021arXiv:2111.10332archive 2025-07-28

Renrui Zhang, Ziyao Zeng, Ziyu Guo, Xinben Gao, Kexue Fu, Jianbo Shi

Point cloud processing is a challenging task due to its sparsity and irregularity. Prior works introduce delicate designs on either local feature aggregator or global geometric architecture, but few combine both advantages. We propose Dual-Scale Point Cloud Recognition with High-frequency Fusion (DSPoint) to extract local-global features by concurrently operating on voxels and points. We reverse the conventional design of applying convolution on voxels and attention to points. Specifically, we disentangle point features through channel dimension for dual-scale processing: one by point-wise convolution for fine-grained geometry parsing, the other by voxel-wise global attention for long-range structural exploration. We design a co-attention fusion module for feature alignment to blend local-global modalities, which conducts inter-scale cross-modality interaction by communicating high-frequency coordinates information. Experiments and ablations on widely-adopted ModelNet40, ShapeNet, and S3DIS demonstrate the state-of-the-art performance of our DSPoint.

PaperPDFCode

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

Code

adonis-galaxy/dspoint officialmentioned in papermentioned 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 Part Segmentation3D Point Cloud Classification3D Shape ClassificationScene SegmentationSemantic SegmentationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Part Segmentation ShapeNet-Part DSPoint Class Average IoU 83.9 #39 of 67 Archive leaderboard report
3D Part Segmentation ShapeNet-Part DSPoint Instance Average IoU 85.8 #39 of 67 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DSPoint Number of params 1.16M #60 of 111 Archive leaderboard report
3D Point Cloud Classification ModelNet40 DSPoint Overall Accuracy 93.5 #60 of 111 Archive leaderboard report
Semantic Segmentation S3DIS DSPoint Mean IoU 63.3 #38 of 54 Archive leaderboard report
Semantic Segmentation S3DIS DSPoint Number of params N/A #38 of 54 Archive leaderboard report
Semantic Segmentation S3DIS DSPoint mAcc 70.9 #38 of 54 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

Convolution

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