MétaCan
Menu
Back to cohort

Point AFNO-Transformer: Adaptive Frequency-Domain Attention for LiDAR Point Cloud Segmentation

2025· article· W7125799892 on OpenAlexaboutno aff
Haiyang Fu, Songdi Jiang, Yangfei Hou, Zichong Yan

Bibliographic record

Venuenot available
Typearticle
Language
FieldEngineering
Topic3D Shape Modeling and Analysis
Canadian institutionsnot available
Fundersnot available
KeywordsPoint cloudSegmentationLidarPoint (geometry)Benchmark (surveying)Artificial neural networkDeep neural networks

Abstract

fetched live from OpenAlex

Semantic segmentation of LiDAR point clouds enables fine-grained understanding of large-scale 3D scenes, yet remains challenging due to the complexity and non-uniformity of real-world data. This paper presents Point AFNO-Transformer, a novel architecture that integrates adaptive frequency-domain attention into a point-based transformer framework. By incorporating a 3D adaptive Fourier neural operator, the network captures contextual dependencies in the frequency domain, complementing the spatial attention mechanism. Experiments on the Toronto-3D benchmark demonstrate that the proposed method achieves superior mean Intersection-over-Union and overall accuracy compared to spatial-domain baselines across most semantic categories. These results suggest that frequencydomain attention offers an effective and efficient alternative to purely spatial attention for large-scale point cloud segmentation, and can foster further advances in 3D scene understanding.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.012
Threshold uncertainty score0.024

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0020.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.011
GPT teacher head0.243
Teacher spread0.232 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topic3D Shape Modeling and AnalysisFrench-language works237,207