4 papers · 1 filter
MDND: Unsupervised Learning Guided by Non-Differentiable Refinement for Shape Correspondence
Qinsong Li, Jing Meng, Haibo Wang +1
Deep functional map frameworks (DFM) for shape correspondence are powerful, yet fundamentally limited by their reliance on end-to-end differentiability. This constraint prevents th…
PAS-Mamba: Phase-Amplitude-Spatial State Space Model for MRI Reconstruction
Xiaoyan Kui, Zijie Fan, Zexin Ji +5
Joint feature modeling in both the spatial and frequency domains has become a mainstream approach in MRI reconstruction. However, existing methods generally treat the frequency dom…
ChebMixer: Efficient Graph Representation Learning with MLP Mixer
Xiaoyan Kui, Haonan Yan, Qinsong Li +2
Graph neural networks have achieved remarkable success in learning graph representations, especially graph Transformer, which has recently shown superior performance on various gra…
Deep Frequency-Aware Functional Maps for Robust Shape Matching
Feifan Luo, Qinsong Li, Ling Hu +4
Deep functional map frameworks are widely employed for 3D shape matching. However, most existing deep functional map methods cannot adaptively capture important frequency informati…