Search Results for author: Jinjin Gu

Found 46 papers, 26 papers with code

Descriptive Image Quality Assessment in the Wild

no code implementations29 May 2024 Zhiyuan You, Jinjin Gu, Zheyuan Li, Xin Cai, Kaiwen Zhu, Chao Dong, Tianfan Xue

We introduce a ground-truth-informed dataset construction approach to enhance data quality, and scale up the dataset to 495K under the brief-detail joint framework.

Descriptive Image Quality Assessment

LM4LV: A Frozen Large Language Model for Low-level Vision Tasks

1 code implementation24 May 2024 BoYang Zheng, Jinjin Gu, Shijun Li, Chao Dong

The success of large language models (LLMs) has fostered a new research trend of multi-modality large language models (MLLMs), which changes the paradigm of various fields in computer vision.

Language Modelling Large Language Model +1

Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning

no code implementations CVPR 2024 Haoyu Chen, Wenbo Li, Jinjin Gu, Jingjing Ren, Haoze Sun, Xueyi Zou, Zhensong Zhang, Youliang Yan, Lei Zhu

Leveraging unseen LR images for self-supervised learning guides the model to adapt its modeling space to the target domain, facilitating fine-tuning of SR models without requiring paired high-resolution (HR) images.

Image Super-Resolution Self-Supervised Learning

Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild

no code implementations CVPR 2024 Fanghua Yu, Jinjin Gu, Zheyuan Li, JinFan Hu, Xiangtao Kong, Xintao Wang, Jingwen He, Yu Qiao, Chao Dong

We introduce SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up.

Descriptive Image Restoration

Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models

1 code implementation14 Dec 2023 Zhiyuan You, Zheyuan Li, Jinjin Gu, Zhenfei Yin, Tianfan Xue, Chao Dong

We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based methods.

Descriptive Image Quality Assessment +1

Image Super-Resolution with Text Prompt Diffusion

1 code implementation24 Nov 2023 Zheng Chen, Yulun Zhang, Jinjin Gu, Xin Yuan, Linghe Kong, Guihai Chen, Xiaokang Yang

Specifically, we first design a text-image generation pipeline to integrate text into the SR dataset through the text degradation representation and degradation model.

Image Generation Image Super-Resolution +1

Binarized 3D Whole-body Human Mesh Recovery

1 code implementation24 Nov 2023 Zhiteng Li, Yulun Zhang, Jing Lin, Haotong Qin, Jinjin Gu, Xin Yuan, Linghe Kong, Xiaokang Yang

In this work, we propose a Binarized Dual Residual Network (BiDRN), a novel quantization method to estimate the 3D human body, face, and hands parameters efficiently.

Binarization Human Mesh Recovery +1

Dual Aggregation Transformer for Image Super-Resolution

1 code implementation ICCV 2023 Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang, Fisher Yu

Based on the above idea, we propose a novel Transformer model, Dual Aggregation Transformer (DAT), for image SR. Our DAT aggregates features across spatial and channel dimensions, in the inter-block and intra-block dual manner.

Image Super-Resolution

Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution

no code implementations29 May 2023 Ruofan Zhang, Jinjin Gu, Haoyu Chen, Chao Dong, Yulun Zhang, Wenming Yang

In this work, we introduce a novel approach to craft training degradation distributions using a small set of reference images.


Hierarchical Integration Diffusion Model for Realistic Image Deblurring

1 code implementation NeurIPS 2023 Zheng Chen, Yulun Zhang, Ding Liu, Bin Xia, Jinjin Gu, Linghe Kong, Xin Yuan

Specifically, we perform the DM in a highly compacted latent space to generate the prior feature for the deblurring process.

Deblurring Image Deblurring +1

Masked Image Training for Generalizable Deep Image Denoising

1 code implementation CVPR 2023 Haoyu Chen, Jinjin Gu, Yihao Liu, Salma Abdel Magid, Chao Dong, Qiong Wang, Hanspeter Pfister, Lei Zhu

To address this issue, we present a novel approach to enhance the generalization performance of denoising networks, known as masked training.

Image Denoising

Recursive Generalization Transformer for Image Super-Resolution

1 code implementation11 Mar 2023 Zheng Chen, Yulun Zhang, Jinjin Gu, Linghe Kong, Xiaokang Yang

In this work, we propose the Recursive Generalization Transformer (RGT) for image SR, which can capture global spatial information and is suitable for high-resolution images.

Image Reconstruction Image Super-Resolution

Xformer: Hybrid X-Shaped Transformer for Image Denoising

1 code implementation11 Mar 2023 Jiale Zhang, Yulun Zhang, Jinjin Gu, Jiahua Dong, Linghe Kong, Xiaokang Yang

The channel-wise Transformer block performs direct global context interactions across tokens defined by channel dimension.

Decoder Image Denoising

DegAE: A New Pretraining Paradigm for Low-Level Vision

1 code implementation CVPR 2023 Yihao Liu, Jingwen He, Jinjin Gu, Xiangtao Kong, Yu Qiao, Chao Dong

However, we argue that pretraining is more significant for high-cost tasks, where data acquisition is more challenging.


Mitigating Artifacts in Real-World Video Super-Resolution Models

1 code implementation14 Dec 2022 Liangbin Xie, Xintao Wang, Shuwei Shi, Jinjin Gu, Chao Dong, Ying Shan

To aggregate a new hidden state that contains fewer artifacts from the hidden state pool, we devise a Selective Cross Attention (SCA) module, in which the attention between input features and each hidden state is calculated.

Video Super-Resolution

Cross Aggregation Transformer for Image Restoration

3 code implementations24 Nov 2022 Zheng Chen, Yulun Zhang, Jinjin Gu, Yongbing Zhang, Linghe Kong, Xin Yuan

The core of our CAT is the Rectangle-Window Self-Attention (Rwin-SA), which utilizes horizontal and vertical rectangle window attention in different heads parallelly to expand the attention area and aggregate the features cross different windows.

Image Restoration Inductive Bias

Self-Supervised Intensity-Event Stereo Matching

no code implementations1 Nov 2022 Jinjin Gu, Jinan Zhou, Ringo Sai Wo Chu, Yan Chen, Jiawei Zhang, Xuanye Cheng, Song Zhang, Jimmy S. Ren

Event cameras are novel bio-inspired vision sensors that output pixel-level intensity changes in microsecond accuracy with a high dynamic range and low power consumption.

Self-Supervised Learning Stereo Matching

Near Real-time CO$_2$ Emissions Based on Carbon Satellite and Artificial Intelligence

no code implementations11 Oct 2022 Zhengwen Zhang, Jinjin Gu, Junhua Zhao, Jianwei Huang, Haifeng Wu

Here we provide the first method that combines the advanced artificial intelligence (AI) techniques and the carbon satellite monitor to quantify anthropogenic CO$_2$ emissions.


Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images

no code implementations9 Oct 2022 Jinjin Gu, Haoming Cai, Chenyu Dong, Ruofan Zhang, Yulun Zhang, Wenming Yang, Chun Yuan

We finally use a guided fusion operation to integrate the sharp edges generated by the network and flat areas by the interpolation method to get the final SR image.

Quantization Super-Resolution

Accurate Image Restoration with Attention Retractable Transformer

1 code implementation4 Oct 2022 Jiale Zhang, Yulun Zhang, Jinjin Gu, Yongbing Zhang, Linghe Kong, Xin Yuan

This is considered as a dense attention strategy since the interactions of tokens are restrained in dense regions.

Denoising Image Restoration +2

NTIRE 2022 Challenge on Perceptual Image Quality Assessment

no code implementations23 Jun 2022 Jinjin Gu, Haoming Cai, Chao Dong, Jimmy S. Ren, Radu Timofte

This challenge is divided into two tracks, a full-reference IQA track similar to the previous NTIRE IQA challenge and a new track that focuses on the no-reference IQA methods.

Image Quality Assessment Image Restoration

Evaluating the Generalization Ability of Super-Resolution Networks

no code implementations14 May 2022 Yihao Liu, Hengyuan Zhao, Jinjin Gu, Yu Qiao, Chao Dong

However, research on the generalization ability of Super-Resolution (SR) networks is currently absent.


Blueprint Separable Residual Network for Efficient Image Super-Resolution

1 code implementation12 May 2022 Zheyuan Li, Yingqi Liu, Xiangyu Chen, Haoming Cai, Jinjin Gu, Yu Qiao, Chao Dong

One is the usage of blueprint separable convolution (BSConv), which takes place of the redundant convolution operation.

Image Super-Resolution

Texture-Based Error Analysis for Image Super-Resolution

no code implementations CVPR 2022 Salma Abdel Magid, Zudi Lin, Donglai Wei, Yulun Zhang, Jinjin Gu, Hanspeter Pfister

Our key contribution is to leverage a texture classifier, which enables us to assign patches with semantic labels, to identify the source of SR errors both globally and locally.

Image Super-Resolution SSIM

Reflash Dropout in Image Super-Resolution

1 code implementation CVPR 2022 Xiangtao Kong, Xina Liu, Jinjin Gu, Yu Qiao, Chao Dong

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR).

Common Sense Reasoning Image Super-Resolution +1

Blind Image Super-Resolution: A Survey and Beyond

no code implementations7 Jul 2021 Anran Liu, Yihao Liu, Jinjin Gu, Yu Qiao, Chao Dong

This paper serves as a systematic review on recent progress in blind image SR, and proposes a taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used for solving the SR model.

Image Super-Resolution

Attention in Attention Network for Image Super-Resolution

2 code implementations19 Apr 2021 Haoyu Chen, Jinjin Gu, Zhi Zhang

In this work, we attempt to quantify and visualize attention mechanisms in SISR and show that not all attention modules are equally beneficial.

Image Super-Resolution

Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric

no code implementations30 Nov 2020 Jinjin Gu, Haoming Cai, Haoyu Chen, Xiaoxing Ye, Jimmy Ren, Chao Dong

To answer the questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing ALgorithms (PIPAL) dataset.

Image Quality Assessment Image Restoration

Interpreting Super-Resolution Networks with Local Attribution Maps

no code implementations CVPR 2021 Jinjin Gu, Chao Dong

Based on LAM, we show that: (1) SR networks with a wider range of involved input pixels could achieve better performance.

Image Super-Resolution

PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

no code implementations ECCV 2020 Jinjin Gu, Haoming Cai, Haoyu Chen, Xiaoxing Ye, Jimmy Ren, Chao Dong

To answer these questions and promote the development of IQA methods, we contribute a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) dataset.

Image Quality Assessment Image Restoration +1

Image Processing Using Multi-Code GAN Prior

1 code implementation CVPR 2020 Jinjin Gu, Yujun Shen, Bolei Zhou

Such an over-parameterization of the latent space significantly improves the image reconstruction quality, outperforming existing competitors.

Blind Face Restoration Colorization +6

Interpreting the Latent Space of GANs for Semantic Face Editing

4 code implementations CVPR 2020 Yujun Shen, Jinjin Gu, Xiaoou Tang, Bolei Zhou

In this work, we propose a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs.

Attribute Disentanglement +2

Suppressing Model Overfitting for Image Super-Resolution Networks

no code implementations11 Jun 2019 Ruicheng Feng, Jinjin Gu, Yu Qiao, Chao Dong

Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved.

Image Super-Resolution Memorization

Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline

1 code implementation7 May 2019 Guocheng Qian, Yuanhao Wang, Jinjin Gu, Chao Dong, Wolfgang Heidrich, Bernard Ghanem, Jimmy S. Ren

In this work, we comprehensively study the effects of pipelines on the mixture problem of learning-based DN, DM, and SR, in both sequential and joint solutions.

Demosaicking Denoising +1

Blind Super-Resolution With Iterative Kernel Correction

3 code implementations CVPR 2019 Jinjin Gu, Hannan Lu, WangMeng Zuo, Chao Dong

In this paper, we propose an Iterative Kernel Correction (IKC) method for blur kernel estimation in blind SR problem, where the blur kernels are unknown.

Blind Super-Resolution Image Super-Resolution

Two-phase Hair Image Synthesis by Self-Enhancing Generative Model

no code implementations28 Feb 2019 Haonan Qiu, Chuan Wang, Hang Zhu, Xiangyu Zhu, Jinjin Gu, Xiaoguang Han

Generating plausible hair image given limited guidance, such as sparse sketches or low-resolution image, has been made possible with the rise of Generative Adversarial Networks (GANs).

Image-to-Image Translation Super-Resolution +2

Super-Resolution Perception for Industrial Sensor Data

no code implementations6 Sep 2018 Jinjin Gu, Haoyu Chen, Guolong Liu, Gaoqi Liang, Xinlei Wang, Junhua Zhao

In this paper, we present the problem formulation and methodology framework of Super-Resolution Perception (SRP) on industrial sensor data.

Fault Detection Super-Resolution

ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks

45 code implementations1 Sep 2018 Xintao Wang, Ke Yu, Shixiang Wu, Jinjin Gu, Yihao Liu, Chao Dong, Chen Change Loy, Yu Qiao, Xiaoou Tang

To further enhance the visual quality, we thoroughly study three key components of SRGAN - network architecture, adversarial loss and perceptual loss, and improve each of them to derive an Enhanced SRGAN (ESRGAN).

Face Hallucination Generative Adversarial Network +2

Single Image Reflection Removal Using Deep Encoder-Decoder Network

3 code implementations31 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.

Decoder Reflection Removal

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