activity
20242026
most citedA Data-driven Loss Weighting Scheme across Heterogeneous Tasks for Image Denoising

1 citations · 1 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV2026

Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process

Yuji Lin, Qian Zhao, Zongsheng Yue +2

This work studies the challenging problem of acquiring high-quality underwater images via 4-D light field (LF) imaging. To this end, we propose GeoDiff-LF, a novel diffusion-based…

eess.IV20261 cited

A Data-driven Loss Weighting Scheme across Heterogeneous Tasks for Image Denoising

Xiangyu Rui, Xiangyong Cao, Xile Zhao +2

In a variational denoising model, weight in the data fidelity term plays the role of enhancing the noise-removal capability. It is profoundly correlated with noise information, whi…

cs.CV2026

Layout-Guided Controllable Pathology Image Generation with In-Context Diffusion Transformers

Yuntao Shou, Xiangyong Cao, Qian Zhao +1

Controllable pathology image synthesis requires reliable regulation of spatial layout, tissue morphology, and semantic detail. However, existing text-guided diffusion models offer…

cs.CV2025

Generative Latent Kernel Modeling for Blind Motion Deblurring

Chenhao Ding, Jiangtao Zhang, Zongsheng Yue +3

Deep prior-based approaches have demonstrated remarkable success in blind motion deblurring (BMD) recently. These methods, however, are often limited by the high non-convexity of t…

cs.CV2025

Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method

Yuji Lin, Junhui Hou, Xianqiang Lyu +2

In this paper, we delve into the realm of 4-D light fields (LFs) to enhance underwater imaging plagued by light absorption, scattering, and other challenges. Contrasting with conve…

cs.CV2025

Singular Value Fine-tuning for Few-Shot Class-Incremental Learning

Zhiwu Wang, Yichen Wu, Renzhen Wang +4

Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while sequentially incorporating new ones. The more challenging Few-shot CIL…