no code implementations • 28 May 2024 • Sike Wang, Jia Li, Pan Zhou, Hua Huang
We show that quantizing the eigenvector matrix of the preconditioner in 4-bit Shampoo is remarkably better than quantizing the preconditioner itself both theoretically and experimentally.
no code implementations • 19 Apr 2024 • Xinlong Ji, Fangneng Zhan, Shijian Lu, Shi-Sheng Huang, Hua Huang
However, the method of generating illumination maps has poor generalization performance and parametric models such as Spherical Harmonic (SH) and Spherical Gaussian (SG) fall short in capturing high-frequency or low-frequency components.
1 code implementation • 17 Mar 2024 • Lin Zhu, Kangmin Jia, Yifan Zhao, Yunshan Qi, Lizhi Wang, Hua Huang
Spike cameras, leveraging spike-based integration sampling and high temporal resolution, offer distinct advantages over standard cameras.
1 code implementation • 10 Mar 2024 • Lin Zhu, Xianzhang Chen, Xiao Wang, Hua Huang
Our framework exhibits a substantial margin of improvement in capturing and highlighting visual saliency in the spike stream, which not only provides a new perspective for spike-based saliency segmentation but also shows a new paradigm for full SNN-based transformer models.
no code implementations • 4 Feb 2024 • Jie Lian, Lizhi Wang, Lin Zhu, Renwei Dian, Zhiwei Xiong, Hua Huang
To fill this gap, we propose physics-inspired degradation models (PIDM) to model the degradation of LR-HSI and HR-MSI, which comprises a spatial degradation network (SpaDN) and a spectral degradation network (SpeDN).
1 code implementation • 25 Jan 2024 • Zheqi He, Xinya Wu, Pengfei Zhou, Richeng Xuan, Guang Liu, Xi Yang, Qiannan Zhu, Hua Huang
However, the mastery of domain-specific knowledge, which is essential for evaluating the intelligence of MLLMs, continues to be a challenge.
no code implementations • 23 Dec 2023 • Yu Cai, Tianyu Shen, Shi-Sheng Huang, Hua Huang
Depth completion, aiming to predict dense depth maps from sparse depth measurements, plays a crucial role in many computer vision related applications.
no code implementations • 20 Dec 2023 • Xin Wang, Lizhi Wang, Xiangtian Ma, Maoqing Zhang, Lin Zhu, Hua Huang
Dual-Camera Compressed Hyperspectral Imaging (DCCHI) offers the capability to reconstruct 3D Hyperspectral Image (HSI) by fusing compressive and Panchromatic (PAN) image, which has shown great potential for snapshot hyperspectral imaging in practice.
1 code implementation • 13 Oct 2023 • Hansen Feng, Lizhi Wang, Yiqi Huang, Yuzhi Wang, Lin Zhu, Hua Huang
Specifically, we integrate physical priors into neural proxies and introduce three efficient techniques: physics-guided noise decoupling (PND), physics-guided proxy model (PPM), and differentiable distribution loss (DDL).
1 code implementation • 6 Aug 2023 • Lin Zhu, Yunlong Zheng, Mengyue Geng, Lizhi Wang, Hua Huang
Spike camera is a new type of bio-inspired vision sensor that records light intensity in the form of a spike array with high temporal resolution (20, 000 Hz).
no code implementations • 12 Jul 2023 • Shi-Sheng Huang, Zi-Xin Zou, Yi-Chi Zhang, Hua Huang
The recent neural surface reconstruction by volume rendering approaches have made much progress by achieving impressive surface reconstruction quality, but are still limited to dense and highly accurate posed views.
1 code implementation • 8 Jul 2023 • Tong Li, Hansen Feng, Lizhi Wang, Zhiwei Xiong, Hua Huang
Image denoising is a fundamental problem in computational photography, where achieving high perception with low distortion is highly demanding.
1 code implementation • 6 Sep 2022 • Yanchao Xu, Wenbo Shao, Jun Li, Kai Yang, Weida Wang, Hua Huang, Chen Lv, Hong Wang
Then, the behaviors of traffic light violations in SIND are recorded.
1 code implementation • 13 Jul 2022 • Hansen Feng, Lizhi Wang, Yuzhi Wang, Hua Huang
Low-light raw denoising is an important and valuable task in computational photography where learning-based methods trained with paired real data are mainstream.
Ranked #1 on Image Denoising on SID SonyA7S2 x100
no code implementations • 30 Jun 2022 • Lingfei Song, Hua Huang
Based on our analysis, we examined the statistics of palmprints and concluded that CompCode deviates from the optimal condition.
2 code implementations • 11 May 2022 • Yawei Li, Kai Zhang, Radu Timofte, Luc van Gool, Fangyuan Kong, Mingxi Li, Songwei Liu, Zongcai Du, Ding Liu, Chenhui Zhou, Jingyi Chen, Qingrui Han, Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Yu Qiao, Chao Dong, Long Sun, Jinshan Pan, Yi Zhu, Zhikai Zong, Xiaoxiao Liu, Zheng Hui, Tao Yang, Peiran Ren, Xuansong Xie, Xian-Sheng Hua, Yanbo Wang, Xiaozhong Ji, Chuming Lin, Donghao Luo, Ying Tai, Chengjie Wang, Zhizhong Zhang, Yuan Xie, Shen Cheng, Ziwei Luo, Lei Yu, Zhihong Wen, Qi Wu1, Youwei Li, Haoqiang Fan, Jian Sun, Shuaicheng Liu, Yuanfei Huang, Meiguang Jin, Hua Huang, Jing Liu, Xinjian Zhang, Yan Wang, Lingshun Long, Gen Li, Yuanfan Zhang, Zuowei Cao, Lei Sun, Panaetov Alexander, Yucong Wang, Minjie Cai, Li Wang, Lu Tian, Zheyuan Wang, Hongbing Ma, Jie Liu, Chao Chen, Yidong Cai, Jie Tang, Gangshan Wu, Weiran Wang, Shirui Huang, Honglei Lu, Huan Liu, Keyan Wang, Jun Chen, Shi Chen, Yuchun Miao, Zimo Huang, Lefei Zhang, Mustafa Ayazoğlu, Wei Xiong, Chengyi Xiong, Fei Wang, Hao Li, Ruimian Wen, Zhijing Yang, Wenbin Zou, Weixin Zheng, Tian Ye, Yuncheng Zhang, Xiangzhen Kong, Aditya Arora, Syed Waqas Zamir, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan, Dandan Gaoand Dengwen Zhouand Qian Ning, Jingzhu Tang, Han Huang, YuFei Wang, Zhangheng Peng, Haobo Li, Wenxue Guan, Shenghua Gong, Xin Li, Jun Liu, Wanjun Wang, Dengwen Zhou, Kun Zeng, Hanjiang Lin, Xinyu Chen, Jinsheng Fang
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
no code implementations • CVPR 2022 • Lingen Li, Lizhi Wang, Weitao Song, Lei Zhang, Zhiwei Xiong, Hua Huang
In this paper, we propose the quantization-aware deep optics for diffractive snapshot hyperspectral imaging.
1 code implementation • 16 Nov 2021 • Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao, Hua Huang
Recently, deep-learning-based super-resolution methods have achieved excellent performances, but mainly focus on training a single generalized deep network by feeding numerous samples.
no code implementations • 31 Jul 2021 • Li Ding, Yongwei Wang, Xin Ding, Kaiwen Yuan, Ping Wang, Hua Huang, Z. Jane Wang
Deep learning based image classification models are shown vulnerable to adversarial attacks by injecting deliberately crafted noises to clean images.
no code implementations • 23 Jun 2021 • Hua Huang, Fanhua Shang, Yuanyuan Liu, Hongying Liu
Unlike existing FL methods, our IGFL can be applied to both client and server optimization.
no code implementations • CVPR 2021 • Shipeng Zhang, Lizhi Wang, Lei Zhang, Hua Huang
Snapshot hyperspectral imaging has been developed to capture the spectral information of dynamic scenes.
1 code implementation • 29 Mar 2021 • Yuanfei Huang, Jie Li, Yanting Hu, Xinbo Gao, Hua Huang
Being extremely dependent on iterative estimation of the degradation prior or optimization of the model from scratch, the existing blind super-resolution (SR) methods are generally time-consuming and less effective, as the estimation of degradation proceeds from a blind initialization and lacks interpretable degradation priors.
no code implementations • 22 Jan 2021 • Niankai Cheng, Hua Huang, Lei Zhang, Lizhi Wang
In this paper, we propose an effective high-order tensor optimization based method to boost the reconstruction fidelity for snapshot hyperspectral imaging.
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.
no code implementations • 19 May 2020 • Lu Ma, Hua Huang, Pei Zhao, Tengrong Su
In this paper, a fusion scheme by combining adaptive filter and neural network is proposed for AEC.
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 #5 on Image Denoising on ELD SonyA7S2 x200
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 • 18 Oct 2019 • Jun Zhou, Hua Huang, Bin Liu, Xiuping Liu
Then we use multi-task optimization to train the normal estimation and local plane classification tasks simultaneously. Also, to integrate the advantages of multi-scale results, a scale selection strategy is adopted, which is a data-driven approach for selecting the optimal scale around each point and encourages subnetwork specialization.
no code implementations • 27 Sep 2019 • Hua Huang, Adrian Barbu
We argue that these instructions have tremendous value in designing a reinforcement learning system which can learn in human fashion, and we test the idea by playing the Atari games Tennis and Pong.
no code implementations • 25 Sep 2019 • Fanhua Shang, Lin Kong, Yuanyuan Liu, Hua Huang, Hongying Liu
Moreover, our theoretical analysis shows that AVR-SExtraGD enjoys the best-known convergence rates and oracle complexities of stochastic first-order algorithms such as Katyusha for both strongly convex and non-strongly convex problems.
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 #2 on Reflection Removal on SIR^2(Objects)
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.