5 papers
Adaptive Dual-Weighted Gravitational Point Cloud Denoising Method
Ge Zhang, Chunyang Wang, Bin Liu +1
High-quality point cloud data is a critical foundation for tasks such as autonomous driving and 3D reconstruction. However, LiDAR-based point cloud acquisition is often affected by…
DM3D: Dynamic Mamba via Offset-Guided Feature Resampling for Point Cloud Understanding
Bin Liu, Chunyang Wang, Xuelian Liu +2
State Space Models (SSMs) model long token sequences of point cloud with linear complexity, but require an unordered point cloud to be serialized. Existing methods mainly address t…
Diverse Normal Prototypes-Guided Contrastive Reconstruction for Medical Anomaly Detection
Luhu Li, Bin Liu, Bowen Lin +3
Anomaly detection in medical images is challenging due to limited annotations and the domain gap. Existing reconstruction-based methods often rely on frozen pre-trained encoders, r…
SM3D: Mitigating Spectral Bias and Semantic Dilution in Point Cloud State Space Models
Bin Liu, Chunyang Wang, Xuelian Liu
Point clouds are a fundamental 3D data representation that underpins various computer vision tasks. Recently, Mamba has demonstrated strong potential for 3D point cloud understandi…
Post-Training Quantization for 3D Medical Image Segmentation: A Practical Study on Real Inference Engines
Chongyu Qu, Ritchie Zhao, Ye Yu +6
Quantizing deep neural networks ,reducing the precision (bit-width) of their computations, can remarkably decrease memory usage and accelerate processing, making these models more…