SRMambaV2: Biomimetic Attention for Sparse Point Cloud Upsampling in Autonomous Driving

2025-07-23

AI Summary

To address the challenges of severe sparsity, significant detail loss in distant regions, and geometric distortion in LiDAR point cloud upsampling for autonomous driving, this paper proposes SRMambaV2—a sparse point cloud super-resolution method inspired by human selective visual perception. Methodologically, it introduces a novel 2D selective scanning self-attention mechanism to capture long-range spatial dependencies; designs a dual-branch feature enhancement network to jointly optimize geometric structure and textural fidelity; and incorporates a progressive adaptive loss function, integrated with range-image projection, to enable efficient 3D–2D joint modeling. Evaluated on benchmark datasets including SemanticKITTI, SRMambaV2 achieves substantial improvements over existing state-of-the-art methods, particularly excelling in reconstructing complex distant topologies and preserving global structural integrity.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Upsampling LiDAR point clouds in autonomous driving scenarios remains a significant challenge due to the inherent sparsity and complex 3D structures of the data. Recent studies have attempted to address this problem by converting the complex 3D spatial scenes into 2D image super-resolution tasks. However, due to the sparse and blurry feature representation of range images, accurately reconstructing detailed and complex spatial topologies remains a major difficulty. To tackle this, we propose a novel sparse point cloud upsampling method named SRMambaV2, which enhances the upsampling accuracy in long-range sparse regions while preserving the overall geometric reconstruction quality. Specifically, inspired by human driver visual perception, we design a biomimetic 2D selective scanning self-attention (2DSSA) mechanism to model the feature distribution in distant sparse areas. Meanwhile, we introduce a dual-branch network architecture to enhance the representation of sparse features. In addition, we introduce a progressive adaptive loss (PAL) function to further refine the reconstruction of fine-grained details during the upsampling process. Experimental results demonstrate that SRMambaV2 achieves superior performance in both qualitative and quantitative evaluations, highlighting its effectiveness and practical value in automotive sparse point cloud upsampling tasks.

Problem

• Upsampling sparse LiDAR point clouds in autonomous driving
• Reconstructing detailed 3D spatial topologies from blurry range images
• Enhancing accuracy in long-range sparse regions while preserving geometry

Innovation

• Biomimetic 2D selective scanning self-attention mechanism
• Dual-branch network enhances sparse feature representation
• Progressive adaptive loss refines fine-grained detail reconstruction