activity
20222025
most citedFast Multi-grid Methods for Minimizing Curvature Energy

14 citations · 28 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2025

Total Normal Curvature Regularization and its Minimization for Surface and Image Smoothing

Tianle Lu, Ke Chen, Yuping Duan

We introduce a novel formulation for curvature regularization by penalizing normal curvatures from multiple directions. This total normal curvature regularization is capable of pro…

cs.CV2024★ 1 cited

LUIEO: A Lightweight Model for Integrating Underwater Image Enhancement and Object Detection

Bin Li, Li Li, Zhenwei Zhang +1

Underwater optical images inevitably suffer from various degradation factors such as blurring, low contrast, and color distortion, which hinder the accuracy of object detection tas…

cs.CV2023★ 7 cited

MetaUE: Model-based Meta-learning for Underwater Image Enhancement

Zhenwei Zhang, Haorui Yan, Ke Tang +1

The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be…

cs.CV2023★ 5 cited

Curvature regularization for Non-line-of-sight Imaging from Under-sampled Data

Rui Ding, Juntian Ye, Qifeng Gao +2

Non-line-of-sight (NLOS) imaging aims to reconstruct the three-dimensional hidden scenes from the data measured in the line-of-sight, which uses photon time-of-flight information e…

eess.IV2022★ 1 cited

CurvPnP: Plug-and-play Blind Image Restoration with Deep Curvature Denoiser

Yutong Li, Yuping Duan

Due to the development of deep learning-based denoisers, the plug-and-play strategy has achieved great success in image restoration problems. However, existing plug-and-play image…

eess.IV2022★ 14 cited

Fast Multi-grid Methods for Minimizing Curvature Energy

Zhenwei Zhang, Ke Chen, Ke Tang +1

The geometric high-order regularization methods such as mean curvature and Gaussian curvature, have been intensively studied during the last decades due to their abilities in prese…