activity
20242026
collaborators

8 papers

math.NA2026

A geometry-based deep equilibrium model for image restoration under multiplicative Gamma noise

Shengkun Yang, Luca Ratti, Zhichang Guo

We propose a deep learning framework for image restoration from images degraded by both multiplicative Gamma noise and blur. Unlike conventional deep equilibrium (DEQ) models that…

cs.CV2026

From level set evolution to threshold optimization: A grayscale level set framework for image segmentation

Xingkai Li, Jiebao Sun, Fanghui Song +1

The segmentation of multiple degradations has been a challenging problem in the field of image segmentation. Existing level set approaches commonly adopt a length regularization te…

cs.CV2026

A Smooth Phase-Separation Model for Weak-Boundary Segmentation of Homogeneous Structures

Zihan Li, Jiebao Sun, Fanghui Song +1

Segmentation of adjacent structures with similar intensity distributions remains a challenging problem in image analysis, particularly when object boundaries are weak or ambiguous.…

cs.CV2026

SILSM: A Sustainable Interactive Level Set Method for Progressive Refinement

Jiachen Song, Dazhi Zhang, Fanghui Song +2

Interactive segmentation aims to precisely isolate target objects using sparse user guidance. However, traditional methods often suffer from heavy interaction burdens and parameter…

math.AP2026

A class of forward-backward regularizations of the Perona-Malik equation with variable exponent

Yihui Tong, Wenjie Liu, Zhichang Guo +1

This paper investigates a novel class of regularizations of the Perona-Malik equation with variable exponents, of forward-backward parabolic type, which possess a variational struc…

cs.CV2025

An ICTM-RMSAV Framework for Bias-Field Aware Image Segmentation under Poisson and Multiplicative Noise

Xinyu Wang, Wenjun Yao, Fanghui Song +1

Image segmentation is a core task in image processing, yet many methods degrade when images are heavily corrupted by noise and exhibit intensity inhomogeneity. Within the iterative…