Abstract
Synergistically capturing intricate local structures and global contextual dependencies has become a critical challenge in point cloud representation learning. To address this, we introduce PointLearner, a point cloud representation learning network that closely aligns with biological vision which employs an active, foveation-inspired processing strategy, thus enabling local geometric modeling and long-range dependency interactions simultaneously. Specifically, we first design a point-focused attention, which simulates foveal vision at the visual focus through a competitive normalized attention mechanism between local neighbors and spatially downsampled features. The spatially downsampled features are extracted by a pooling method based on learnable inducing points, which can flexibly adapt to the non-uniform distribution of point clouds as the number of inducing points is controlled and they interact directly with point clouds. Second, we propose a context-scan state space that mimics eye's saccade inference, which infers the overall semantic structure and spatial content in the scene through a scan path guided by the Hilbert curve for the bidirectional S6. With this focus-then-context biomimetic design, PointLearner demonstrates remarkable robustness and achieves state-of-the-art performance across multiple point cloud tasks.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Qu, K., Gao, P., Dai, Q., & Sun, Y. (2026). Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation. https://omanscience.com/en/articles/point-focused-attention-meets-context-scan-state-space-robust-biological-visual-perception-for-point-cloud-representation
MLA 9
Qu, Kanglin, et al. "Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation." https://omanscience.com/en/articles/point-focused-attention-meets-context-scan-state-space-robust-biological-visual-perception-for-point-cloud-representation.
Chicago (author–date)
Qu, Kanglin, Pan Gao, Qun Dai, and Yuanhao Sun. 2026. "Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation." https://omanscience.com/en/articles/point-focused-attention-meets-context-scan-state-space-robust-biological-visual-perception-for-point-cloud-representation.
Harvard
Qu, K., Gao, P., Dai, Q. and Sun, Y. (2026) 'Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation', Available at: https://omanscience.com/en/articles/point-focused-attention-meets-context-scan-state-space-robust-biological-visual-perception-for-point-cloud-representation.
Vancouver
Qu K, Gao P, Dai Q, Sun Y. Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation. https://omanscience.com/en/articles/point-focused-attention-meets-context-scan-state-space-robust-biological-visual-perception-for-point-cloud-representation
IEEE
K. Qu, P. Gao, Q. Dai, and Y. Sun, "Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation," https://omanscience.com/en/articles/point-focused-attention-meets-context-scan-state-space-robust-biological-visual-perception-for-point-cloud-representation.