Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Kyoung Mu Lee

Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report


May 17, 2021
Andrey Ignatov, Andres Romero, Heewon Kim, Radu Timofte, Chiu Man Ho, Zibo Meng, Kyoung Mu Lee, Yuxiang Chen, Yutong Wang, Zeyu Long, Chenhao Wang, Yifei Chen, Boshen Xu, Shuhang Gu, Lixin Duan, Wen Li, Wang Bofei, Zhang Diankai, Zheng Chengjian, Liu Shaoli, Gao Si, Zhang Xiaofeng, Lu Kaidi, Xu Tianyu, Zheng Hui, Xinbo Gao, Xiumei Wang, Jiaming Guo, Xueyi Zhou, Hao Jia, Youliang Yan

* Mobile AI 2021 Workshop and Challenges: https://ai-benchmark.com/workshops/mai/2021/. arXiv admin note: substantial text overlap with arXiv:2105.07825. substantial text overlap with arXiv:2105.08629, arXiv:2105.07809, arXiv:2105.08630 

  Access Paper or Ask Questions

NTIRE 2021 Challenge on Video Super-Resolution


May 10, 2021
Sanghyun Son, Suyoung Lee, Seungjun Nah, Radu Timofte, Kyoung Mu Lee

* An official report for NTIRE 2021 Video Super-Resolution Challenge, in conjunction with CVPR 2021 

  Access Paper or Ask Questions

NTIRE 2021 Challenge on Image Deblurring


Apr 30, 2021
Seungjun Nah, Sanghyun Son, Suyoung Lee, Radu Timofte, Kyoung Mu Lee

* To be published in CVPR 2021 Workshop - NTIRE 

  Access Paper or Ask Questions

Clean Images are Hard to Reblur: A New Clue for Deblurring


Apr 26, 2021
Seungjun Nah, Sanghyun Son, Jaerin Lee, Kyoung Mu Lee


  Access Paper or Ask Questions

SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation


Apr 21, 2021
Sanghyun Son, Kyoung Mu Lee

* Accepted to CVPR 2021 

  Access Paper or Ask Questions

3DCrowdNet: 2D Human Pose-Guided3D Crowd Human Pose and Shape Estimation in the Wild


Apr 15, 2021
Hongsuk Choi, Gyeongsik Moon, JoonKyu Park, Kyoung Mu Lee

* also attached the supplementary material 

  Access Paper or Ask Questions

DAQ: Distribution-Aware Quantization for Deep Image Super-Resolution Networks


Dec 21, 2020
Cheeun Hong, Heewon Kim, Junghun Oh, Kyoung Mu Lee


  Access Paper or Ask Questions

Searching for Controllable Image Restoration Networks


Dec 21, 2020
Heewon Kim, Sungyong Baik, Myungsub Choi, Janghoon Choi, Kyoung Mu Lee


  Access Paper or Ask Questions

NeuralAnnot: Neural Annotator for in-the-wild Expressive 3D Human Pose and Mesh Training Sets


Nov 28, 2020
Gyeongsik Moon, Kyoung Mu Lee


  Access Paper or Ask Questions

Pose2Pose: 3D Positional Pose-Guided 3D Rotational Pose Prediction for Expressive 3D Human Pose and Mesh Estimation


Nov 28, 2020
Gyeongsik Moon, Kyoung Mu Lee


  Access Paper or Ask Questions

Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video


Nov 26, 2020
Hongsuk Choi, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee


  Access Paper or Ask Questions

DynaVSR: Dynamic Adaptive Blind Video Super-Resolution


Nov 09, 2020
Suyoung Lee, Myungsub Choi, Kyoung Mu Lee


  Access Paper or Ask Questions

Meta-Learning with Adaptive Hyperparameters


Oct 31, 2020
Sungyong Baik, Myungsub Choi, Janghoon Choi, Heewon Kim, Kyoung Mu Lee

* NeurIPS 2020. Code at https://github.com/baiksung/alfa 

  Access Paper or Ask Questions

AIM 2020 Challenge on Video Temporal Super-Resolution


Sep 28, 2020
Sanghyun Son, Jaerin Lee, Seungjun Nah, Radu Timofte, Kyoung Mu Lee

* Published in ECCV 2020 Workshop (Advances in Image Manipulation) 

  Access Paper or Ask Questions

Domain Adaptation of Learned Features for Visual Localization


Aug 21, 2020
Sungyong Baik, Hyo Jin Kim, Tianwei Shen, Eddy Ilg, Kyoung Mu Lee, Chris Sweeney

* BMVC 2020 

  Access Paper or Ask Questions

InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image


Aug 21, 2020
Gyeongsik Moon, Shoou-i Yu, He Wen, Takaaki Shiratori, Kyoung Mu Lee

* Published at ECCV 2020 

  Access Paper or Ask Questions

Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose


Aug 20, 2020
Hongsuk Choi, Gyeongsik Moon, Kyoung Mu Lee

* Published at ECCV 2020 

  Access Paper or Ask Questions

DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling


Aug 19, 2020
Gyeongsik Moon, Takaaki Shiratori, Kyoung Mu Lee

* Published at ECCV 2020 (Oral) 

  Access Paper or Ask Questions

I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image


Aug 09, 2020
Gyeongsik Moon, Kyoung Mu Lee

* Published at ECCV 2020 

  Access Paper or Ask Questions

Visual Tracking by TridentAlign and Context Embedding


Jul 14, 2020
Janghoon Choi, Junseok Kwon, Kyoung Mu Lee

* Code available on https://github.com/JanghoonChoi/TACT 

  Access Paper or Ask Questions

IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos


Jul 13, 2020
Gyeongsik Moon, Heeseung Kwon, Kyoung Mu Lee, Minsu Cho


  Access Paper or Ask Questions

NTIRE 2020 Challenge on Image and Video Deblurring


May 10, 2020
Seungjun Nah, Sanghyun Son, Radu Timofte, Kyoung Mu Lee

* To be published in CVPR 2020 Workshop (New Trends in Image Restoration and Enhancement) 

  Access Paper or Ask Questions

AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results


May 04, 2020
Seungjun Nah, Sanghyun Son, Radu Timofte, Kyoung Mu Lee

* 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW), Seoul, Korea (South), 2019, pp. 3388-3398 
* Published in ICCV 2019 Workshop (Advances in Image Manipulation) 

  Access Paper or Ask Questions

Scene-Adaptive Video Frame Interpolation via Meta-Learning


Apr 02, 2020
Myungsub Choi, Janghoon Choi, Sungyong Baik, Tae Hyun Kim, Kyoung Mu Lee

* CVPR 2020 

  Access Paper or Ask Questions

Fine-Grained Neural Architecture Search


Nov 18, 2019
Heewon Kim, Seokil Hong, Bohyung Han, Heesoo Myeong, Kyoung Mu Lee


  Access Paper or Ask Questions