chldydgh4687 Goto Github PK

followers: 5.0 following: 8.0 repos: 28.0 gists: 2.0

Name: Yongho Choi

Type: User

Company: IVCL,Sejong University

Bio: Super-Resolution / MPEG-I / VCM

Location: Seoul, South Korea

🔭Graduation

M.S. - Intelligent Visual Computing Lab, Sejong Univ.2021.03 – Present
B.S. - School of Intelligent Mechatronics Engineering, Sejong University, Feb. 2021

🔭 Focusing on major.

VideoCoding [VVC,MPEG-I(MIV),VCM]
DeepLearning [SuperResolution,S2VT]

🔭 Environment Skills

C++ / Python
Video Understanding (TMIV/VCM/VTM)
pytorch, tensorflow2
ffmpeg(OpenSW)
Docker, git management

🔭 Publications

International Journal

*“Immersive Video Coding Using Deep Learning Based Specular Detection”, Association for the Advancement of Artificial Intelligence (Under Review)
“Specular Detection and Rendering for Immersive Multimedia”, IEEE Multimedia (Major Revisions)
“Efficient Video Captioning Using Quality Enhancement in Video Communication Systems”, Expert Systems with Applications (Under Review)
“Low-Complexity Two-Step Lossless Depth Coding Using Coarse Lossy Coding”, Multimedia Tools and Applications, Apr. 2022
“Low-Complexity Intra Coding in Versatile Video Coding”, IEEE Trans. Consumer Electronics, May 2022
*:First Order

Domestic Journal

*"몰입형 입체 영상 부호화를 위한 VVC 인루프 필터 성능 분석", 2022 한국방송미디어공학회 추계학술대회

🔭 Standardization

*[MPEG-I] “Future MPEG Immersive Video Coding Based on Specular Detection”, m57981, Oct.2021
*[MPEG-I] “Deep Learning Based Specular Pruning”, m58997, Jan.2022
[MPEG-I] "The crosscheck report for EE4.a in Future MIV exploration experiment", m56611, April.2021
[MPEG-I] "Results for EE3 on Future MIV", m57492, July.2021
[VVC] “AHG11:Deep Neural Network for Super-Resolution”, JVET-T0096, Oct.2020
[VCM] “VVC tool combination for efficient feature map coding”, m60128, Jul.2022
[VCM] “Performance analysis of VVC inter tools for feature map coding”, m60127, Jul.2022
[VCM] “Performance analysis of VVC intra tools for feature map coding”, m60126, Jul.2022
*:First Order

🔭 Patents

[출원] “영상의 화질에 따라 초해상도 딥러닝 네트워크를 적용하는 비디오 처리 방법 및 비디오 처리 장치”, 10-2022-0011541

More_Detail(Not ready) : https://chldydgh4687.github.io

Yongho Choi's Projects

08_2020-1.creative.videocaptioning

2020-1.SEJONG.Univ_Summer_Creative_Semester : 저화질 영상에 대한 Video Captioning 네트워크 성능 향상 연구

08_2021-1.ivcl-summerschool

2021-1.IVCL-SummerSchool(HEVC/SuperResolutions)

08_detectron2

Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks.

09_2019-1.situationclassfier_demo-fail-

SejongUniversity_AI termproject_Demo(Fail).2019

09_2019-2.prp.spatialpyramidmatching

2019-2.SEJONG_패턴인식프로젝트 SPM캐글 191008 ~ 191214

09_2020-1.aimp.cardclassification

2020-1.SEJONG_인공지능미니프로젝트 : Card_image_classification

09_2020-2.webprogramming.gitpage

2020-2.WebProgramming.gitpage

09_2021-2.computervision_dcscn_pytorch

2021-2.ComputerVision_DCSCN_pytorch ( Reference : https://github.com/jiny2001/dcscn-super-resolution )

09_2021-2.cv_monoculardepthestimation2recon

09_2021-2.ComputerVision_MonocularDepthEstimationRecon_pytorch

09_2021-2.cv_ther2rgb-translationrecon

2021-2.CV_Ther2RGB-TranslationRecon

Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.