1 code implementation • 24 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.
1 code implementation • 7 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.
2 code implementations • ICCV 2023 • JinYuan Liu, Zhu Liu, Guanyao Wu, Long Ma, Risheng Liu, Wei Zhong, Zhongxuan Luo, Xin Fan
Multi-modality image fusion and segmentation play a vital role in autonomous driving and robotic operation.
Ranked #3 on Semantic Segmentation on FMB Dataset
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.
no code implementations • 14 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.
1 code implementation • 25 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.
no code implementations • 29 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.
1 code implementation • 20 Nov 2022 • JinYuan Liu, Runjia Lin, Guanyao Wu, Risheng Liu, Zhongxuan Luo, Xin Fan
Infrared and visible image fusion targets to provide an informative image by combining complementary information from different sensors.
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.
1 code implementation • CVPR 2022 • JinYuan Liu, Xin Fan, Zhanbo Huang, Guanyao Wu, Risheng Liu, Wei Zhong, Zhongxuan Luo
This study addresses the issue of fusing infrared and visible images that appear differently for object detection.
Ranked #1 on Object Detection on Multispectral Dataset
1 code implementation • 14 Mar 2022 • Xin Fan, Zi Li, Ziyang Li, Xiaolin Wang, Risheng Liu, Zhongxuan Luo, Hao Huang
Deformable image registration plays a critical role in various tasks of medical image analysis.
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.
1 code implementation • 9 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.
1 code implementation • 9 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).
2 code implementations • 26 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).
1 code implementation • ICCV 2021 • Miao Zhang, Jie Liu, Yifei Wang, Yongri Piao, Shunyu Yao, Wei Ji, Jingjing Li, Huchuan Lu, Zhongxuan Luo
Our bidirectional dynamic fusion strategy encourages the interaction of spatial and temporal information in a dynamic manner.
Ranked #12 on Video Polyp Segmentation on SUN-SEG-Easy (Unseen)
1 code implementation • 10 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.
1 code implementation • CVPR 2021 • Risheng Liu, Long Ma, Jiaao Zhang, Xin Fan, Zhongxuan Luo
Low-light image enhancement plays very important roles in low-level vision field.
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.
2 code implementations • 30 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.
no code implementations • 29 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.
no code implementations • 18 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.
no code implementations • 17 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.
no code implementations • 8 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.
1 code implementation • 15 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.
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.
no code implementations • 9 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.
no code implementations • 16 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.
2 code implementations • 9 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.
no code implementations • 31 Jul 2018 • Risheng Liu, Yi He, Shichao Cheng, Xin Fan, Zhongxuan Luo
Blind image deblurring plays a very important role in many vision and multimedia applications.
no code implementations • 5 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.
no code implementations • 26 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.
no code implementations • 28 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.
no code implementations • 23 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.
no code implementations • 21 Nov 2017 • Risheng Liu, Xin Fan, Shichao Cheng, Xiangyu Wang, Zhongxuan Luo
Deep learning models have gained great success in many real-world applications.
no code implementations • 18 Nov 2017 • Risheng Liu, Xin Fan, Minjun Hou, Zhiying Jiang, Zhongxuan Luo, Lei Zhang
However, they may fail when their assumptions are not valid on specific images.
2 code implementations • 26 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.