1 code implementation • 2 Jun 2023 • Zeqiang Lai, Yuchen Duan, Jifeng Dai, Ziheng Li, Ying Fu, Hongsheng Li, Yu Qiao, Wenhai Wang
In this paper, we propose to ameliorate the semantic segmentation quality of existing discriminative approaches with a mask prior modeled by a recently-developed denoising diffusion generative model.
1 code implementation • 27 Apr 2023 • Linwei Chen, Ying Fu, Kaixuan Wei, Dezhi Zheng, Felix Heide
Existing instance segmentation techniques are primarily tailored for high-visibility inputs, but their performance significantly deteriorates in extremely low-light environments.
1 code implementation • CVPR 2023 • Miaoyu Li, Ji Liu, Ying Fu, Yulun Zhang, Dejing Dou
In this paper, we address these issues by proposing a spectral enhanced rectangle Transformer, driving it to explore the non-local spatial similarity and global spectral low-rank property of HSIs.
1 code implementation • CVPR 2023 • Zichun Wang, Ying Fu, Ji Liu, Yulun Zhang
Despite the significant results on synthetic noise under simplified assumptions, most self-supervised denoising methods fail under real noise due to the strong spatial noise correlation, including the advanced self-supervised blind-spot networks (BSNs).
1 code implementation • 16 Mar 2023 • Zeqiang Lai, Ying Fu
Challenges in adapting transformer for HSI arise from the capabilities to tackle existing limitations of CNN-based methods in capturing the global and local spatial-spectral correlations while maintaining efficiency and flexibility.
no code implementations • 24 Feb 2023 • Chao Hu, Ruishi Yu, Binqi Zeng, Yu Zhan, Ying Fu, Quan Zhang, Rongkai Liu, Heyuan Shi
Hypergraph neural networks (HGNN) have shown superior performance in various deep learning tasks, leveraging the high-order representation ability to formulate complex correlations among data by connecting two or more nodes through hyperedge modeling.
no code implementations • 13 Feb 2023 • Zeqiang Lai, Ying Fu, Jun Zhang
The features of RGB reference images are then processed by a multi-stage alignment module to explicitly align the features of RGB reference with the LR HSI.
1 code implementation • 27 Jan 2023 • Zeqiang Lai, Ying Fu
However, existing methods show limitations in exploring the spectral correlations across different bands and feature interactions within each band.
no code implementations • CVPR 2023 • Kang Ma, Ying Fu, Dezhi Zheng, Chunshui Cao, Xuecai Hu, Yongzhen Huang
Specifically, we create a dynamic attention mechanism between the features of neighboring pixels that not only adaptively focuses on key regions but also generates more expressive local motion patterns.
no code implementations • 27 Nov 2022 • Zeqiang Lai, Ying Fu
Hyperspectral image is unique and useful for its abundant spectral bands, but it subsequently requires extra elaborated treatments of the spatial-spectral correlation as well as the global correlation along the spectrum for building a robust and powerful HSI restoration algorithm.
3 code implementations • 25 Nov 2022 • Miaoyu Li, Ying Fu, Yulun Zhang
Hyperspectral image (HSI) denoising is a crucial preprocessing procedure for the subsequent HSI applications.
no code implementations • 10 Oct 2022 • Fan Zhang, ShaoDi You, Yu Li, Ying Fu
In this paper, we propose GTAV-NightRain dataset, which is a large-scale synthetic night-time rain streak removal dataset.
1 code implementation • 17 Sep 2022 • Zeqiang Lai, Kaixuan Wei, Ying Fu
Deep-learning-based hyperspectral image (HSI) restoration methods have gained great popularity for their remarkable performance but often demand expensive network retraining whenever the specifics of task changes.
no code implementations • 7 Apr 2022 • Yuemei Zhou, Tao Yu, Zerong Zheng, Ying Fu, Yebin Liu
Existing state-of-the-art novel view synthesis methods rely on either fairly accurate 3D geometry estimation or sampling of the entire space for neural volumetric rendering, which limit the overall efficiency.
no code implementations • CVPR 2022 • Yunhao Zou, Ying Fu
In this work, we combine both noise modeling and estimation, and propose an innovative noise model estimation and noise synthesis pipeline for realistic noisy image generation.
1 code implementation • 20 Mar 2022 • Weijia Wu, Yuanqiang Cai, Chunhua Shen, Debing Zhang, Ying Fu, Hong Zhou, Ping Luo
Recent video text spotting methods usually require the three-staged pipeline, i. e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results.
no code implementations • 8 Mar 2022 • Lipei Zhang, Yiran Wei, Ying Fu, Stephen Price, Carola-Bibiane Schönlieb, Chao Li
In this proposed scheme, we design a normalized modality contrastive loss (NMC-loss), which could promote to disentangle multi-modality complementary representation of FFPE and frozen sections from the same patient.
1 code implementation • 4 Aug 2021 • Kaixuan Wei, Ying Fu, Yinqiang Zheng, Jiaolong Yang
Enhancing the visibility in extreme low-light environments is a challenging task.
Ranked #2 on Image Denoising on SID x300
no code implementations • 23 Jul 2021 • Yixiao Yang, Ran Tao, Kaixuan Wei, Ying Fu
In this paper, a dynamic proximal unrolling network (dubbed DPUNet) was proposed, which can handle a variety of measurement matrices via one single model without retraining.
1 code implementation • CVPR 2021 • Fan Zhang, Yu Li, ShaoDi You, Ying Fu
Based on this idea, we propose our method which can infer motion prior for single image low light video enhancement and enforce temporal consistency.
no code implementations • CVPR 2021 • Yunhao Zou, Yinqiang Zheng, Tsuyoshi Takatani, Ying Fu
Event cameras are novel sensors that capture the dynamics of a scene asynchronously.
no code implementations • ICCV 2021 • Ruizhi Shao, Gaochang Wu, Yuemei Zhou, Ying Fu, Yebin Liu
By combining the local transformer with the multiscale structure, the network is able to capture long-short range correspondences efficiently and accurately.
1 code implementation • 26 May 2021 • Yuxuan Han, Jiaolong Yang, Ying Fu
We further propose a Disentanglement-Transformation (DT) metric to quantify the attribute transformation and disentanglement efficacy and find the optimal control factor between attribute-level and instance-specific directions based on it.
no code implementations • 4 Jan 2021 • Qiye Liu, Le Wang, Ying Fu, Xi Zhang, Lianglong Huang, Huimin Su, Junhao Lin, Xiaobin Chen, Dapeng Yu, Xiaodong Cui, Jia-Wei Mei, Jun-Feng Dai
Mermin-Wagner-Coleman theorem predicts no long-range magnetic order at finite temperature in the two-dimensional (2D) isotropic systems, but a quasi-long-range order with a divergent correlation length at the Kosterlitz-Thouless (KT) transition for planar magnets.
Mesoscale and Nanoscale Physics
1 code implementation • ICCV 2021 • Tao Zhang, Ying Fu, Cheng Li
On the other hand, we propose an accurate HSI noise model which matches the distribution of real data well and can be employed to synthesize realistic dataset.
no code implementations • 18 Dec 2020 • Yuxing Huang, ShaoDi You, Ying Fu, Qiu Shen
It is based on the idea that high-resolution HSIs in city scenes contain rich spectral information, which can be easily associated to semantics without manual labeling.
Semi-Supervised Semantic Segmentation Weakly supervised Semantic Segmentation +1
no code implementations • NeurIPS 2020 • Zhuokun Yao, Kun Li, Ying Fu, Haofeng Hu, Boxin Shi
For all-pixel operation, we propose the Normal Regression Network to make efficient use of the intra-image spatial information for predicting a surface normal map with rich details.
no code implementations • CVPR 2021 • Yuemei Zhou, Gaochang Wu, Ying Fu, Kun Li, Yebin Liu
Various combinations of cameras enrich computational photography, among which reference-based superresolution (RefSR) plays a critical role in multiscale imaging systems.
1 code implementation • 18 Nov 2020 • Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang, Ying Fu, Hua Huang, Carola-Bibiane Schönlieb
In this work, we present a class of tuning-free PnP proximal algorithms that can determine parameters such as denoising strength, termination time, and other optimization-specific parameters automatically.
6 code implementations • 11 Oct 2020 • Xiang An, Xuhan Zhu, Yang Xiao, Lan Wu, Ming Zhang, Yuan Gao, Bin Qin, Debing Zhang, Ying Fu
The experiment demonstrates no loss of accuracy when training with only 10\% randomly sampled classes for the softmax-based loss functions, compared with training with full classes using state-of-the-art models on mainstream benchmarks.
Ranked #2 on Face Identification on MegaFace
1 code implementation • 30 Jun 2020 • Di Wu, Qi Tang, Yongle Zhao, Ming Zhang, Ying Fu, Debing Zhang
The 8 bits quantization has been widely applied to accelerate network inference in various deep learning applications.
1 code implementation • CVPR 2020 • Kaixuan Wei, Ying Fu, Jiaolong Yang, Hua Huang
Lacking rich and realistic data, learned single image denoising algorithms generalize poorly to real raw images that do not resemble the data used for training.
Ranked #1 on Image Denoising on ELD SonyA7S2 x100
2 code implementations • 10 Mar 2020 • Kaixuan Wei, Ying Fu, Hua Huang
In this paper, we propose an alternating directional 3D quasi-recurrent neural network for hyperspectral image (HSI) denoising, which can effectively embed the domain knowledge -- structural spatio-spectral correlation and global correlation along spectrum.
1 code implementation • ICML 2020 • Kaixuan Wei, Angelica Aviles-Rivero, Jingwei Liang, Ying Fu, Carola-Bibiane Schönlieb, Hua Huang
Moreover, we discuss the practical considerations of the plugged denoisers, which together with our learned policy yield state-of-the-art results.
no code implementations • 24 Jul 2019 • Shaodi You, Erqi Huang, Shuaizhe Liang, Yongrong Zheng, Yunxiang Li, Fan Wang, Sen Lin, Qiu Shen, Xun Cao, Diming Zhang, Yuanjiang Li, Yu Li, Ying Fu, Boxin Shi, Feng Lu, Yinqiang Zheng, Robby T. Tan
This document introduces the background and the usage of the Hyperspectral City Dataset and the benchmark.
no code implementations • CVPR 2019 • Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang
To overcome the limitations of existing hyperspectral cameras on spatial/temporal resolution, fusing a low resolution hyperspectral image (HSI) with a high resolution RGB (or multispectral) image into a high resolution HSI has been prevalent.
1 code implementation • CVPR 2019 • Kaixuan Wei, Jiaolong Yang, Ying Fu, David Wipf, Hua Huang
Removing undesirable reflections from a single image captured through a glass window is of practical importance to visual computing systems.
Ranked #1 on Reflection Removal on SIR^2(Objects)
no code implementations • ECCV 2018 • Ying Fu, Tao Zhang, Yinqiang Zheng, Debing Zhang, Hua Huang
Hyperspectral image (HSI) recovery from a single RGB image has attracted much attention, whose performance has recently been shown to be sensitive to the camera spectral sensitivity (CSS).
no code implementations • 2 Jun 2017 • Guangtao Nie, Ying Fu, Yinqiang Zheng, Hua Huang
A series of methods have been proposed to reconstruct an image from compressively sensed random measurement, but most of them have high time complexity and are inappropriate for patch-based compressed sensing capture, because of their serious blocky artifacts in the restoration results.
no code implementations • CVPR 2016 • Ying Fu, Yinqiang Zheng, Imari Sato, Yoichi Sato
In this paper, we propose an effective method for coded hyperspectral image restoration, which exploits extensive structure sparsity in the hyperspectral image.
no code implementations • ICCV 2015 • Ying Fu, Antony Lam, Imari Sato, Yoichi Sato
Hyperspectral imaging is beneficial in a diverse range of applications from diagnostic medicine, to agriculture, to surveillance to name a few.
no code implementations • ICCV 2015 • Yinqiang Zheng, Ying Fu, Antony Lam, Imari Sato, Yoichi Sato
This paper introduces a novel method to separate fluorescent and reflective components in the spectral domain.
no code implementations • CVPR 2014 • Ying Fu, Antony Lam, Yasuyuki Kobashi, Imari Sato, Takahiro Okabe, Yoichi Sato
We then show that given the spectral reflectance and fluorescent chromaticity, the fluorescence absorption and emission spectra can also be estimated.