activity
20232026
most citedReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learning

48 citations · 76 across the 4 of their papers we have counts for

collaborators

6 papers

math.DG2026

Ricci flows and bracket flows on twisted principal bundles

Henry Wood

We show that Ricci flows of invariant metrics on twisted principal bundles with nilpotent fibres over \(S^1\) are immortal and type III. After normalisation and lift to the univers…

cs.CV2026

Spatial-Spectral Interactive POCS Network for Large-Gap Seismic Data Interpolation

Baisong Jiang, Chunxia Zhang, Anxiang Di +4

Large gaps in seismic acquisition disrupt reflection events and hinder spectral recovery. Existing seismic interpolation deep unfolding networks primarily rely on localized spatial…

physics.geo-ph2025

Efficient Seismic Data Interpolation via Sparse Attention Transformer and Diffusion Model

Xiaoli Wei, Chunxia Zhang, Baisong Jiang +4

Seismic data interpolation is a critical pre-processing step for improving seismic imaging quality and remains a focus of academic innovation. To address the computational ineffici…

cs.CV2025★ 18 cited

Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis

Haowen Bai, Zixiang Zhao, Jiangshe Zhang +5

Multi-modal image fusion synthesizes information from multiple sources into a single image, facilitating downstream tasks such as semantic segmentation. Current approaches primaril…

cs.CV2023★ 48 cited

ReFusion: Learning Image Fusion from Reconstruction with Learnable Loss via Meta-Learning

Haowen Bai, Zixiang Zhao, Jiangshe Zhang +5

Image fusion aims to combine information from multiple source images into a single one with more comprehensive informational content. Deep learning-based image fusion algorithms fa…

physics.geo-ph2023★ 10 cited

Seismic Data Interpolation via Denoising Diffusion Implicit Models with Coherence-corrected Resampling

Xiaoli Wei, Chunxia Zhang, Hongtao Wang +5

Accurate interpolation of seismic data is crucial for improving the quality of imaging and interpretation. In recent years, deep learning models such as U-Net and generative advers…