IEEE

Electrical Impedance Tomography Deep Imaging With Dual-Branch U-Net Based on Deformable Convolution and Hyper-Convolution

Abstract: Electrical impedance tomography (EIT) is a new imaging modality for nonionizing radiation that uses a safe current applied to the surface and measures the response voltage on a boundary ...
GitHub

Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation

LiDAR point cloud semantic segmentation enables the robots to obtain fine-grained semantic information of the surrounding environment. Recently, many works project the point cloud onto the 2D image ...
IEEE

KNLConv: Kernel-Space Non-Local Convolution for Hyperspectral Image Super-Resolution

Abstract: Pixel-level adaptive convolution, which overcomes the deficiency of the spatial-invariance of standard convolution, is always limited to performing feature extraction from local patches and ...
GitHub

ESC: Emulating Self-attention with Convolution for Efficient Image Super-Resolution

In this paper, we tackle the high computational overhead of transformers for lightweight image super-resolution. (SR). Motivated by the observations of self-attention's inter-layer repetition, we ...