Shengwei Tian

DiffVec: Diffusion Model for Trajectory Vector Recovery

The increasing availability of trajectory data is often hampered by sparsity and noise. Existing trajectory recovery methods are further limited by either information loss from coordinate discretization into location IDs, or the inefficiency of conventional diffusion models that require a lengthy denoising process from...

DPSAM2: memory-guided dual-path adaptation of SAM2 for boundary-aware low-contrast segmentation

GeoSFLoRA: Geometry-Conditioned Spectral Flow Low-Rank Adaptation for 2D-to-3D Transfer in Medical Image Segmentation

GeoSFLoRA consistently improves Dice and HD95 on BraTS20, MSD-Prostate, and MSD-Lung, approaching full fine-tuning performance and demonstrating an effective paradigm for 2D-to-3D medical image segmentation.