122 citations · 634 across the 39 of their papers we have counts for
19 papers · 1 filter
Automated Learning for Deformable Medical Image Registration by Jointly Optimizing Network Architectures and Objective Functions
Xin Fan, Zi Li, Ziyang Li +4
Deformable image registration plays a critical role in various tasks of medical image analysis. A successful registration algorithm, either derived from conventional energy optimiz…
Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision
Risheng Liu, Long Ma, Tengyu Ma +2
Images captured from low-light scenes often suffer from severe degradations, including low visibility, color cast and intensive noises, etc. These factors not only affect image qua…
An Underwater Image Semantic Segmentation Method Focusing on Boundaries and a Real Underwater Scene Semantic Segmentation Dataset
Zhiwei Ma, Haojie Li, Zhihui Wang +5
With the development of underwater object grabbing technology, underwater object recognition and segmentation of high accuracy has become a challenge. The existing underwater objec…
Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement
Risheng Liu, Long Ma, Jiaao Zhang +2
Low-light image enhancement plays very important roles in low-level vision field. Recent works have built a large variety of deep learning models to address this task. However, the…
Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision
Risheng Liu, Zhu Liu, Pan Mu +2
In recent years, there has been a growing interest in combining learnable modules with numerical optimization to solve low-level vision tasks. However, most existing approaches foc…
Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond
Risheng Liu, Zi Li, Xin Fan +3
Conventional deformable registration methods aim at solving an optimization model carefully designed on image pairs and their computational costs are exceptionally high. In contras…
Investigating Task-driven Latent Feasibility for Nonconvex Image Modeling
Risheng Liu, Pan Mu, Jian Chen +2
Properly modeling latent image distributions plays an important role in a variety of image-related vision problems. Most exiting approaches aim to formulate this problem as optimiz…
Underexposed Image Correction via Hybrid Priors Navigated Deep Propagation
Risheng Liu, Long Ma, Yuxi Zhang +2
Enhancing visual qualities for underexposed images is an extensively concerned task that plays important roles in various areas of multimedia and computer vision. Most existing met…
Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions
Risheng Liu, Xin Fan, Ming Zhu +2
Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years. These algorithms develop…
A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI
Risheng Liu, Yuxi Zhang, Shichao Cheng +2
Magnetic Resonance Imaging (MRI) is one of the most dynamic and safe imaging techniques available for clinical applications. However, the rather slow speed of MRI acquisitions limi…
On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems
Risheng Liu, Shichao Cheng, Yi He +3
Numerous tasks at the core of statistics, learning and vision areas are specific cases of ill-posed inverse problems. Recently, learning-based (e.g., deep) iterative methods have b…
User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks
Yuanzheng Ci, Xinzhu Ma, Zhihui Wang +2
Scribble colors based line art colorization is a challenging computer vision problem since neither greyscale values nor semantic information is presented in line arts, and the lack…
Learning Collaborative Generation Correction Modules for Blind Image Deblurring and Beyond
Risheng Liu, Yi He, Shichao Cheng +2
Blind image deblurring plays a very important role in many vision and multimedia applications. Most existing works tend to introduce complex priors to estimate the sharp image stru…
A Single Shot Text Detector with Scale-adaptive Anchors
Qi Yuan, Bingwang Zhang, Haojie Li +2
Currently, most top-performing text detection networks tend to employ fixed-size anchor boxes to guide the search for text instances. They usually rely on a large amount of anchors…
Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization
Risheng Liu, Shichao Cheng, Yi He +2
Operator splitting methods have been successfully used in computational sciences, statistics, learning and vision areas to reduce complex problems into a series of simpler subprobl…
Proximal Alternating Direction Network: A Globally Converged Deep Unrolling Framework
Risheng Liu, Xin Fan, Shichao Cheng +2
Deep learning models have gained great success in many real-world applications. However, most existing networks are typically designed in heuristic manners, thus lack of rigorous m…
Self-Reinforced Cascaded Regression for Face Alignment
Xin Fan, Risheng Liu, Kang Huyan +2
Cascaded regression is prevailing in face alignment thanks to its accuracy and robustness, but typically demands manually annotated examples having low discrepancy between shape-in…
Learning Aggregated Transmission Propagation Networks for Haze Removal and Beyond
Risheng Liu, Xin Fan, Minjun Hou +3
Single image dehazing is an important low-level vision task with many applications. Early researches have investigated different kinds of visual priors to address this problem. How…
A Fast Ellipse Detector Using Projective Invariant Pruning
Qi Jia, Xin Fan, Zhongxuan Luo +2
Detecting elliptical objects from an image is a central task in robot navigation and industrial diagnosis where the detection time is always a critical issue. Existing methods are…