5 papers
U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training
Zhiwen Yang, Jiayin Li, Hao Lu +3
Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restr…
Multi-Resolution Alignment for Voxel Sparsity in Camera-Based 3D Semantic Scene Completion
Zhiwen Yang, Yuxin Peng
Camera-based 3D semantic scene completion (SSC) offers a cost-effective solution for assessing the geometric occupancy and semantic labels of each voxel in the surrounding 3D scene…
CausalFSFG: Rethinking Few-Shot Fine-Grained Visual Categorization from Causal Perspective
Zhiwen Yang, Jinglin Xu, Yuxin Pen
Few-shot fine-grained visual categorization (FS-FGVC) focuses on identifying various subcategories within a common superclass given just one or few support examples. Most existing…
HD-SSC: High-Dimension High-Density Semantic Scene Completion for Autonomous Driving
Zhiwen Yang, Yuxin Peng
Camera-based 3D semantic scene completion (SSC) plays a crucial role in autonomous driving, enabling voxelized 3D scene understanding for effective scene perception and decision-ma…
SPHERE: Semantic-PHysical Engaged REpresentation for 3D Semantic Scene Completion
Zhiwen Yang, Yuxin Peng
Camera-based 3D Semantic Scene Completion (SSC) is a critical task in autonomous driving systems, assessing voxel-level geometry and semantics for holistic scene perception. While…