User profiles for Chen Change Loy
![]() | Chen Change LoyMMLab@NTU, S-Lab, Nanyang Technological University Verified email at ntu.edu.sg Cited by 83434 |
Learning a deep convolutional network for image super-resolution
We propose a deep learning method for single image super-resolution (SR). Our method
directly learns an end-to-end mapping between the low/high-resolution images. The mapping …
directly learns an end-to-end mapping between the low/high-resolution images. The mapping …
Image super-resolution using deep convolutional networks
We propose a deep learning method for single image super-resolution (SR). Our method
directly learns an end-to-end mapping between the low/high-resolution images. The mapping …
directly learns an end-to-end mapping between the low/high-resolution images. The mapping …
Edvr: Video restoration with enhanced deformable convolutional networks
… 1, 5, 6 [7] Tak-Wai Hui, Xiaoou Tang, and Chen Change Loy. … 2, 3 [8] Tak-Wai Hui, Xiaoou
Tang, and Chen Change Loy. A … Dong, Liang Lin, and Chen Change Loy. Crafting a toolchain …
Tang, and Chen Change Loy. A … Dong, Liang Lin, and Chen Change Loy. Crafting a toolchain …
Domain generalization: A survey
… In (a), the domain shift mainly corresponds to changes in font style, color and background. …
caused by changes in environment/scene and viewpoint. In (c), image style changes are the …
caused by changes in environment/scene and viewpoint. In (c), image style changes are the …
Self-supervised representation learning: Introduction, advances, and challenges
Self-supervised representation learning (SSRL) methods aim to provide powerful, deep
feature learning without the requirement of large annotated data sets, thus alleviating the …
feature learning without the requirement of large annotated data sets, thus alleviating the …
Image aesthetic assessment: An experimental survey
This article reviews recent computer vision techniques used in the assessment of image
aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-…
aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-…
Esrgan: Enhanced super-resolution generative adversarial networks
The Super-Resolution Generative Adversarial Network (SRGAN) is a seminal work that is
capable of generating realistic textures during single image super-resolution. However, the …
capable of generating realistic textures during single image super-resolution. However, the …
MMDetection: Open mmlab detection toolbox and benchmark
We present MMDetection, an object detection toolbox that contains a rich set of object detection
and instance segmentation methods as well as related components and modules. The …
and instance segmentation methods as well as related components and modules. The …
Learning to prompt for vision-language models
Large pre-trained vision-language models like CLIP have shown great potential in learning
representations that are transferable across a wide range of downstream tasks. Different …
representations that are transferable across a wide range of downstream tasks. Different …
Conditional prompt learning for vision-language models
With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential
to investigate ways to adapt these models to downstream datasets. A recently proposed …
to investigate ways to adapt these models to downstream datasets. A recently proposed …