Search Results for author: Zhongxuan Luo

Found 37 papers, 21 papers with code

Learning Heavily-Degraded Prior for Underwater Object Detection

1 code implementation24 Aug 2023 Chenping Fu, Xin Fan, Jiewen Xiao, Wanqi Yuan, Risheng Liu, Zhongxuan Luo

Therefore, we propose a residual feature transference module (RFTM) to learn a mapping between deep representations of the heavily degraded patches of DFUI- and underwater- images, and make the mapping as a heavily degraded prior (HDP) for underwater detection.

Object object-detection +1

Bilevel Generative Learning for Low-Light Vision

1 code implementation7 Aug 2023 Yingchi Liu, Zhu Liu, Long Ma, JinYuan Liu, Xin Fan, Zhongxuan Luo, Risheng Liu

In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain.

Bilevel Optimization

DPM-OT: A New Diffusion Probabilistic Model Based on Optimal Transport

1 code implementation ICCV 2023 Zezeng Li, Shenghao Li, Zhanpeng Wang, Na lei, Zhongxuan Luo, Xianfeng GU

Sampling from diffusion probabilistic models (DPMs) can be viewed as a piecewise distribution transformation, which generally requires hundreds or thousands of steps of the inverse diffusion trajectory to get a high-quality image.

Denoising Knowledge Distillation

OT-Net: A Reusable Neural Optimal Transport Solver

no code implementations14 Jun 2023 Zezeng Li, Shenghao Li, Lianbao Jin, Na lei, Zhongxuan Luo

With the widespread application of optimal transport (OT), its calculation becomes essential, and various algorithms have emerged.

Domain Adaptation Image Generation

A Task-guided, Implicitly-searched and Meta-initialized Deep Model for Image Fusion

1 code implementation25 May 2023 Risheng Liu, Zhu Liu, JinYuan Liu, Xin Fan, Zhongxuan Luo

Qualitative and quantitative experimental results on different categories of image fusion problems and related downstream tasks (e. g., visual enhancement and semantic understanding) substantiate the flexibility and effectiveness of our TIM.

Practical Exposure Correction: Great Truths Are Always Simple

no code implementations29 Dec 2022 Long Ma, Tianjiao Ma, Xinwei Xue, Xin Fan, Zhongxuan Luo, Risheng Liu

Improving the visual quality of the given degraded observation by correcting exposure level is a fundamental task in the computer vision community.

Toward Fast, Flexible, and Robust Low-Light Image Enhancement

1 code implementation CVPR 2022 Long Ma, Tengyu Ma, Risheng Liu, Xin Fan, Zhongxuan Luo

Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios.

Computational Efficiency Face Detection +2

Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way

1 code implementation CVPR 2022 Qi Jia, Shuilian Yao, Yu Liu, Xin Fan, Risheng Liu, Zhongxuan Luo

To tackle camouflaged object detection (COD), we are inspired by humans attention coupled with the coarse-to-fine detection strategy, and thereby propose an iterative refinement framework, coined SegMaR, which integrates Segment, Magnify and Reiterate in a multi-stage detection fashion.

object-detection Object Detection

Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement

1 code implementation9 Dec 2021 Long Ma, Risheng Liu, Jiaao Zhang, Xin Fan, Zhongxuan Luo

Further, by sharing an encoder for these two components, we obtain a more lightweight version (SLiteCSDNet for short).

Low-Light Image Enhancement

Learning with Nested Scene Modeling and Cooperative Architecture Search for Low-Light Vision

1 code implementation9 Dec 2021 Risheng Liu, Long Ma, Tengyu Ma, Xin Fan, Zhongxuan Luo

To partially address above issues, we establish Retinex-inspired Unrolling with Architecture Search (RUAS), a general learning framework, which not only can address low-light enhancement task, but also has the flexibility to handle other more challenging downstream vision applications.

Rolling Shutter Correction

An Underwater Image Semantic Segmentation Method Focusing on Boundaries and a Real Underwater Scene Semantic Segmentation Dataset

2 code implementations26 Aug 2021 Zhiwei Ma, Haojie Li, Zhihui Wang, Dan Yu, Tianyi Wang, Yingshuang Gu, Xin Fan, Zhongxuan Luo

Based on this dataset, we propose a semi-supervised underwater semantic segmentation network focusing on the boundaries(US-Net: Underwater Segmentation Network).

Boundary Detection Instance Segmentation +7

Optimization-Inspired Learning with Architecture Augmentations and Control Mechanisms for Low-Level Vision

1 code implementation10 Dec 2020 Risheng Liu, Zhu Liu, Pan Mu, Xin Fan, Zhongxuan Luo

Specifically, by introducing a general energy minimization model and formulating its descent direction from different viewpoints (i. e., in a generative manner, based on the discriminative metric and with optimality-based correction), we construct three propagative modules to effectively solve the optimization models with flexible combinations.

AE-OT: A NEW GENERATIVE MODEL BASED ON EXTENDED SEMI-DISCRETE OPTIMAL TRANSPORT

1 code implementation ICLR 2020 Dongsheng An, Yang Guo, Na lei, Zhongxuan Luo, Shing-Tung Yau, Xianfeng GU

In order to tackle the both problems, we explicitly separate the manifold embedding and the optimal transportation; the first part is carried out using an autoencoder to map the images onto the latent space; the second part is accomplished using a GPU-based convex optimization to find the discontinuous transportation maps.

Learning Deformable Image Registration from Optimization: Perspective, Modules, Bilevel Training and Beyond

2 code implementations30 Apr 2020 Risheng Liu, Zi Li, Xin Fan, Chenying Zhao, Hao Huang, Zhongxuan Luo

We design a new deep learning based framework to optimize a diffeomorphic model via multi-scale propagation in order to integrate advantages and avoid limitations of these two categories of approaches.

Image Registration Image Segmentation +1

Converged Deep Framework Assembling Principled Modules for CS-MRI

no code implementations29 Oct 2019 Risheng Liu, Yuxi Zhang, Shichao Cheng, Zhongxuan Luo, Xin Fan

Compressed Sensing Magnetic Resonance Imaging (CS-MRI) significantly accelerates MR data acquisition at a sampling rate much lower than the Nyquist criterion.

Investigating Task-driven Latent Feasibility for Nonconvex Image Modeling

no code implementations18 Oct 2019 Risheng Liu, Pan Mu, Jian Chen, Xin Fan, Zhongxuan Luo

Properly modeling latent image distributions plays an important role in a variety of image-related vision problems.

Deblurring Image Deblurring

Underexposed Image Correction via Hybrid Priors Navigated Deep Propagation

no code implementations17 Jul 2019 Risheng Liu, Long Ma, Yuxi Zhang, Xin Fan, Zhongxuan Luo

Plenty of experimental results of underexposed image correction demonstrate that our proposed method performs favorably against the state-of-the-art methods on both subjective and objective assessments.

Face Detection Single Image Haze Removal

Mode Collapse and Regularity of Optimal Transportation Maps

no code implementations8 Feb 2019 Na lei, Yang Guo, Dongsheng An, Xin Qi, Zhongxuan Luo, Shing-Tung Yau, Xianfeng GU

This work builds the connection between the regularity theory of optimal transportation map, Monge-Amp\`{e}re equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficulty and mode collapse.

Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions

1 code implementation15 Jan 2019 Risheng Liu, Xin Fan, Ming Zhu, Minjun Hou, Zhongxuan Luo

Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years.

Image Enhancement object-detection +1

A Bridging Framework for Model Optimization and Deep Propagation

no code implementations NeurIPS 2018 Risheng Liu, Shichao Cheng, Xiaokun Liu, Long Ma, Xin Fan, Zhongxuan Luo

Different from these existing network based iterations, which often lack theoretical investigations, we provide strict convergence analysis for PODM in the challenging nonconvex and nonsmooth scenarios.

Model Optimization

A Theoretically Guaranteed Deep Optimization Framework for Robust Compressive Sensing MRI

no code implementations9 Nov 2018 Risheng Liu, Yuxi Zhang, Shichao Cheng, Xin Fan, Zhongxuan Luo

Magnetic Resonance Imaging (MRI) is one of the most dynamic and safe imaging techniques available for clinical applications.

Compressive Sensing

On the Convergence of Learning-based Iterative Methods for Nonconvex Inverse Problems

no code implementations16 Aug 2018 Risheng Liu, Shichao Cheng, Yi He, Xin Fan, Zhouchen Lin, Zhongxuan Luo

Moreover, there is a lack of rigorous analysis about the convergence behaviors of these reimplemented iterations, and thus the significance of such methods is a little bit vague.

Scheduling

User-Guided Deep Anime Line Art Colorization with Conditional Adversarial Networks

2 code implementations9 Aug 2018 Yuanzheng Ci, Xinzhu Ma, Zhihui Wang, Haojie Li, Zhongxuan Luo

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 of authentic illustration-line art training pairs also increases difficulty of model generalization.

Benchmarking Line Art Colorization

A Single Shot Text Detector with Scale-adaptive Anchors

no code implementations5 Jul 2018 Qi Yuan, Bingwang Zhang, Haojie Li, Zhihui Wang, Zhongxuan Luo

Currently, most top-performing text detection networks tend to employ fixed-size anchor boxes to guide the search for text instances.

Computational Efficiency Text Detection

Geometric Understanding of Deep Learning

no code implementations26 May 2018 Na Lei, Zhongxuan Luo, Shing-Tung Yau, David Xianfeng Gu

In this work, we give a geometric view to understand deep learning: we show that the fundamental principle attributing to the success is the manifold structure in data, namely natural high dimensional data concentrates close to a low-dimensional manifold, deep learning learns the manifold and the probability distribution on it.

Machine Translation speech-recognition +2

Toward Designing Convergent Deep Operator Splitting Methods for Task-specific Nonconvex Optimization

no code implementations28 Apr 2018 Risheng Liu, Shichao Cheng, Yi He, Xin Fan, Zhongxuan Luo

Operator splitting methods have been successfully used in computational sciences, statistics, learning and vision areas to reduce complex problems into a series of simpler subproblems.

Deblurring

Self-Reinforced Cascaded Regression for Face Alignment

no code implementations23 Nov 2017 Xin Fan, Risheng Liu, Kang Huyan, Yuyao Feng, Zhongxuan Luo

Cascaded regression is prevailing in face alignment thanks to its accuracy and robustness, but typically demands manually annotated examples having low discrepancy between shape-indexed features and shape updates.

Face Alignment Philosophy +1

A Fast Ellipse Detector Using Projective Invariant Pruning

2 code implementations26 Aug 2016 Qi Jia, Xin Fan, Zhongxuan Luo, Lianbo Song, Tie Qiu

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.

Robot Navigation

Cannot find the paper you are looking for? You can Submit a new open access paper.