no code implementations • 24 Jan 2024 • Xi Zhang, Xiaolin Wu
Recently, DNN models for lossless image coding have surpassed their traditional counterparts in compression performance, reducing the bit rate by about ten percent for natural color images.
no code implementations • 3 Jul 2023 • Yanhui Guo, Fangzhou Luo, Xiaolin Wu
Image signal processing (ISP) pipeline plays a fundamental role in digital cameras, which converts raw Bayer sensor data to RGB images.
no code implementations • CVPR 2023 • Xi Zhang, Xiaolin Wu
Recently, numerous end-to-end optimized image compression neural networks have been developed and proved themselves as leaders in rate-distortion performance.
no code implementations • 13 Feb 2023 • Xi Zhang, Xiaolin Wu
In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer.
1 code implementation • 11 Sep 2022 • Yuanchao Bai, Xianming Liu, Kai Wang, Xiangyang Ji, Xiaolin Wu, Wen Gao
In the lossless mode, the DLPR coding system first performs lossy compression and then lossless coding of residuals.
no code implementations • 24 Jan 2022 • Muhammad Umair Mukati, Xi Zhang, Xiaolin Wu, Søren Forchhammer
To enrich the functionalities of traditional cameras, light field cameras record both the intensity and direction of light rays, so that images can be rendered with user-defined camera parameters via computations.
no code implementations • NeurIPS 2021 • Fangzhou Luo, Xiaolin Wu, Yanhui Guo
In this work, we propose a novel system called functional neural network (FuncNet) to solve a parametric image restoration problem with a single model.
no code implementations • 5 Aug 2021 • Yanhui Guo, Xiaolin Wu, Xiao Shu
The resulting LR$\sim$HR image pairs can be aligned at very high sub-pixel precision by a novel spatial-frequency dual-domain registration method, and hence they provide more appropriate training data for the learning task of super-resolution.
no code implementations • 5 Jul 2021 • Xi Zhang, Xiaolin Wu
Arguably the most common and salient object in daily video communications is the talking head, as encountered in social media, virtual classrooms, teleconferences, news broadcasting, talk shows, etc.
no code implementations • 18 Jun 2021 • Chang Liu, Xiaolin Wu
Nighttime photographers are often troubled by light pollution of unwanted artificial lights.
no code implementations • CVPR 2021 • Xi Zhang, Xiaolin Wu
We propose a deep learning system for attention-guided dual-layer image compression (AGDL).
no code implementations • NeurIPS 2020 • Xi Zhang, Xiaolin Wu
With the above critique we ask the question what if a deep convolutional neural network is carefully trained for numerosity?
no code implementations • 2 Aug 2020 • Yanhui Guo, Xi Zhang, Xiaolin Wu
We propose a novel deep multi-modality neural network for restoring very low bit rate videos of talking heads.
no code implementations • 14 Mar 2020 • Qiang Li, Xian-Ming Liu, Kaige Han, Cheng Guo, Xiangyang Ji, Xiaolin Wu
Whole slide imaging (WSI) is an emerging technology for digital pathology.
no code implementations • 10 Feb 2020 • Xi Zhang, Xiaolin Wu
We make a major progress in $\ell_\infty$-constrained image coding after two decades, by developing a novel CNN-based soft $\ell_\infty$-constrained decoding method.
no code implementations • 28 Jan 2020 • Seyed Mehdi Ayyoubzadeh, Xiaolin Wu
We present a CNN-based predictive lossless compression scheme for raw color mosaic images of digital cameras.
no code implementations • 21 Jan 2020 • Seyed Mehdi Ayyoubzadeh, Xiaolin Wu
We have shown that the proposed method can recover fine details of the images and it is stable in the training process.
no code implementations • 30 Jul 2019 • Xi Zhang, Xiaolin Wu, Jun Du
Given the success of the deep convolutional neural networks (DCNNs) in applications of visual recognition and classification, it would be tantalizing to test if DCNNs can also learn spatial concepts, such as straightness, convexity, left/right, front/back, relative size, aspect ratio, polygons, etc., from varied visual examples of these concepts that are simple and yet vital for spatial reasoning.
no code implementations • 25 Jul 2019 • Seyed Mehdi Ayyoubzadeh, Xiaolin Wu
Regularization techniques are widely used to improve the generality, robustness, and efficiency of deep convolutional neural networks (DCNNs).
no code implementations • ICLR 2019 • Fangzhou Luo, Xiaolin Wu
We propose a general method for various image restoration problems, such as denoising, deblurring, super-resolution and inpainting.
no code implementations • 18 Nov 2018 • Bolin Liu, Xiao Shu, Xiaolin Wu
In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world.
no code implementations • 30 Oct 2018 • Xi Zhang, Xiaolin Wu
Deep convolutional neural networks (DCNN) have enjoyed great successes in many signal processing applications because they can learn complex, non-linear causal relationships from input to output.
no code implementations • 11 Apr 2018 • Bolin Liu, Xiao Shu, Xiaolin Wu
Taking photos of optoelectronic displays is a direct and spontaneous way of transferring data and keeping records, which is widely practiced.
no code implementations • 5 Mar 2018 • Chang Liu, Xiaolin Wu, Xiao Shu
All existing image enhancement methods, such as HDR tone mapping, cannot recover A/D quantization losses due to insufficient or excessive lighting, (underflow and overflow problems).
no code implementations • 9 Feb 2018 • Xiaolin Wu, Xi Zhang, Xiao Shu
Subitizing, or the sense of small natural numbers, is an innate cognitive function of humans and primates; it responds to visual stimuli prior to the development of any symbolic skills, language or arithmetic.
3 code implementations • 31 Jan 2018 • Zhixiang Chi, Xiaolin Wu, Xiao Shu, Jinjin Gu
Image of a scene captured through a piece of transparent and reflective material, such as glass, is often spoiled by a superimposed layer of reflection image.
no code implementations • 18 Jan 2018 • Xi Zhang, Xiaolin Wu
Recently a number of CNN-based techniques were proposed to remove image compression artifacts.
no code implementations • 18 Jul 2017 • Bolin Liu, Xiao Shu, Xiaolin Wu
This paper presents a generic pre-processor for expediting conventional template matching techniques.
no code implementations • 11 Dec 2016 • Xiaolin Wu, Xi Zhang, Chang Liu
This article is a sequel to our earlier work [25].
no code implementations • 13 Nov 2016 • Xiaolin Wu, Xi Zhang
In November 2016 we submitted to arXiv our paper "Automated Inference on Criminality Using Face Images".
no code implementations • 7 Jul 2016 • Xianming Liu, Gene Cheung, Xiaolin Wu, Debin Zhao
In this paper, we combine three image priors---Laplacian prior for DCT coefficients, sparsity prior and graph-signal smoothness prior for image patches---to construct an efficient JPEG soft decoding algorithm.
no code implementations • 6 Jan 2016 • Xiao Shu, Xiaolin Wu
Small compression noises, despite being transparent to human eyes, can adversely affect the results of many image restoration processes, if left unaccounted for.
no code implementations • ICCV 2015 • Xiaolin Wu, Zhenhao Li, Xiaowei Deng
A common video degradation problem, which is largely untreated in literature, is what we call Yin-Yang Phasing (YYP).
no code implementations • CVPR 2015 • Xianming Liu, Xiaolin Wu, Jiantao Zhou, Debin Zhao
Arguably the most common cause of image degradation is compression.