High-fidelity point cloud generation via multi-scale attentive feature fusion with graphSAGE and transformer

Yunyun Zhang

doi:10.1007/s00371-026-04389-y

High-fidelity point cloud generation via multi-scale attentive feature fusion with graphSAGE and transformer

10.1007/s00371-026-04389-y

2026-02-28

0

PRE

AI

Save

Share

Original

0Request

Assist

Abstract

En 中文

In 3D point cloud generation tasks, traditional geometric optimization methods struggle to capture complex structures in high-dimensional spaces. Deep learning-based attention mechanisms, Transformers, and graph convolutional networks have significantly improved point cloud representation and generation quality in recent years. However, existing approaches often fail to simultaneously capture multi-scale geometric features while effectively coupling local and global structures. We propose PointAttn-TransGraphNet, an integrated framework for multi-scale attentive feature fusion and point-wise local–global coupling. On the encoder side, PointAttention adaptively aggregates point-wise cues into a global token that is refined by a lightweight Transformer at very low cost. On the decoder side, a GraphSAGE-based hierarchy performs mean aggregation message passing with residual connections on k-nearest neighbor graphs across stages, yielding explicit multi-scale representations; at each upsampling stage, a fusion MLP injects the encoder’s global token into per-point local features, achieving point-wise local–global feature fusion while increasing resolution. We evaluate on two complementary tracks. On ShapeNet, our method achieves consistent and significant advantages across the vast majority of metrics. On ModelNet40, we follow an unsupervised representation learning protocol and report linear evaluation accuracy, where our features outperform strong baselines. Meanwhile, the model attains smaller parameter counts and lower inference time while maintaining comparable FLOPs, validating the effectiveness of the lightweight design. Ablations show that, although compute is decoder-dominated, deepening the lightweight encoder improves global semantics with negligible overhead; module ablations further confirm their complementary roles in multi-scale decoding. The code and data supporting this study are available at https://github.com/zhangyunyun1/PointAttn-TransGraphNet (DOI: https://doi.org/10.5281/zenodo.15303929 ).

Keywords:

Point cloud generation

Multi-scale feature fusion

Lightweight transformer

Hierarchical graphSAGE decoder

Point-wise local–global fusion

High-fidelity point cloud generation via multi-scale attentive feature fusion with graphSAGE and transformer

Abstract

Journal

Researchers

Organization

Cited Papers

Citing Papers