Dae-Young Song

Research Scientist

I’m a research scientist at Electronics and Telecommunications Research Institute (ETRI) (Daejeon, South Korea).

Currently, I am working on generative models based on VISION AI for artworks.

Email: eadyoung@naver.com ; eadgaudiyoung@gmail.com

Publications

2023

  1. CVPR 2023
    DIFu: Depth-guided Implicit Function for Clothed Human Reconstruction
    Dae-Young Song, HeeKyung Lee, Jeongil Seo, and Donghyeon Cho

2022

  1. ECCV 2022
    Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation
    Dae-Young Song, Geonsoo Lee, HeeKyung Lee, Gi-Mun Um, and Donghyeon Cho

2021

  1. IEEE SPL
    End-to-End Image Stitching Network via Multi-Homography Estimation
    Dae-Young Song, Gi-Mun Um, HeeKyung Lee, and Donghyeon Cho


Projects

2023

  1. Development of Artificial Intelligence-based Photo/Painting Harmonization and Content Expansion Technology
    Korea Creative Content Agency (KOCCA)

2022

  1. 3D Digital Human Reconstruction
    Electronics and Telecommunications Research Institute (ETRI), Institute of Information & communications Technology Planning & Evaluation (IITP)

2021

  1. 360 Real-Scene Panorama Generation using Deep Neural Network
    Electronics and Telecommunications Research Institute (ETRI), Institute of Information & communications Technology Planning & Evaluation (IITP)

2020

  1. APAP Image Stitching Re-implementation with Python
    Dae-Young Song
  2. Correcting Artifact Caused by Depth Difference
    Electronics and Telecommunications Research Institute (ETRI)


Patents

2022

  1. METHOD AND APPARATUS FOR GENERATING PANORAMIC IMAGE BASED ON DEEP LEARNING NETWORK (US 17/951,899)
    HeeKyung Lee, Gi-Mun Um, Dae-Young Song, Donghyeon Cho
  2. 딥러닝 네트워크 기반의 파노라마 영상 생성 방법 및 장치 (KR 10-2022-0065357)
    Gi-Mun Um, HeeKyung Lee, Dae-Young Song, Donghyeon Cho

2021

  1. DEEP LEARNING-BASED IMAGE STITCHING METHOD AND APPARATUS (US 17/532,880)
    Gi-Mun Um, HeeKyung Lee, Dae-Young Song, Donghyeon Cho

2020

  1. 시차에 강인한 영상 정합을 위한 신경망 방법 및 장치 (KR 10-2020-0160113)
    Gi-Mun Um, HeeKyung Lee, Dae-Young Song, Donghyeon Cho