|
 코드번호 : 39 |
|
| 발표자 : 김형신 |
|
| 소속 : 서울대 |
|
| 부서 : |
|
| 직위 : 교수 |
|
| 세션시간 : 16:00~17:50 |
|
| 발표자약력 : |
서울대학교 데이터사이언스대학원 교수 (2020 ~ 현재)
Google 소프트웨어 엔지니어 (2019 ~ 2020)
UC Berkeley 전기컴퓨터공학부 Postdoc (2016 ~ 2019)
서울대학교 전기컴퓨터공학부 박사 (~2016) |
|
|
| 강연요약 : |
We present MIRROR, an on-device video virtual try-on (VTO) system that provides realistic, private, and rapid experiences in mobile clothes shopping. Despite recent advancements in generative adversarial networks (GANs) for VTO, designing MIRROR involves two challenges: (1) data discrepancy due to restricted training data that miss various poses, body sizes, and background
ds and (2) loputation overhead that uses up 24% of battery for converting only a single video. To alleviate the problems, we propose a generalizable VTO GAN that not only discerns intricate human body semantics but also captures domain-invariant features without requiring additional training data. In addition, we craft lightweight, reliable clothes/pose-tracking that generates refined pixel-wise warping flow without neural-net computation. As a holistic system, MIRROR integrates the new VTO GAN and tracking method with meticulous pre/post-processing, operating in two distinct phases (on/offline). Our results on Android smartphones and real-world user videos show that compared to a cutting-edge VTO GAN, MIRROR achieves 6.5× better accuracy with 20.1× faster video conversion and 16.9× less energy consumption. |
|
|
|
facebook