activity
20232026
most citedWhere Do We Stand with Implicit Neural Representations? A Technical and Performance Survey

6 citations · 6 across the 4 of their papers we have counts for

collaborators

9 papers

cs.CV2026

ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection

Chun-Wun Cheng, Yanqi Cheng, Peiyuan Jing +4

Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution…

cs.CV2025

DNA-Prior: Unsupervised Denoise Anything via Dual-Domain Prior

Yanqi Cheng, Chun-Wun Cheng, Jim Denholm +5

Medical imaging pipelines critically rely on robust denoising to stabilise downstream tasks such as segmentation and reconstruction. However, many existing denoisers depend on larg…

eess.IV2025

From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction

Zhenxuan Zhang, Lipei Zhang, Yanqi Cheng +10

In motion-robust magnetic resonance imaging (MRI), slice-to-volume reconstruction is critical for recovering anatomically consistent 3D brain volumes from 2D slices, especially und…

cs.CV2025

Deep Spectral Prior

Yanqi Cheng, Xuxiang Zhao, Tieyong Zeng +3

We introduce the Deep Spectral Prior (DSP), a new framework for unsupervised image reconstruction that operates entirely in the complex frequency domain. Unlike the Deep Image Prio…

eess.IV2025

D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction

Lipei Zhang, Rui Sun, Zhongying Deng +3

Variations in Magnetic resonance imaging (MRI) scanners and acquisition protocols cause distribution shifts that degrade reconstruction performance on unseen data. Test-time adapta…

eess.IV2025

Implicit U-KAN2.0: Dynamic, Efficient and Interpretable Medical Image Segmentation

Chun-Wun Cheng, Yining Zhao, Yanqi Cheng +3

Image segmentation is a fundamental task in both image analysis and medical applications. State-of-the-art methods predominantly rely on encoder-decoder architectures with a U-shap…