ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 SC-FEGAN: Face Editing Generative Adversarial Network with User’s Sketch and Color
Cited 40 time in scopus Download 11 time Share share facebook twitter linkedin kakaostory
저자
조영주, 박종열
발행일
201910
출처
International Conference on Computer Vision (ICCV) 2019, pp.1745-1753
DOI
https://dx.doi.org/10.1109/ICCV.2019.00183
협약과제
19HS3400, (딥뷰-1세부) 실시간 대규모 영상 데이터 이해·예측을 위한 고성능 비주얼 디스커버리 플랫폼 개발, 박종열
초록
We present a novel image editing system that generates images as the user provides free-form masks, sketches and color as inputs. Our system consists of an end-to-end trainable convolutional network. In contrast to the existing methods, our system utilizes entirely free-form user input in terms of color and shape. This allows the system to respond to the user's sketch and color inputs, using them as guidelines to generate an image. In this work, we trained the network with an additional style loss, which made it possible to generate realistic results despite large portions of the image being removed. Our proposed network architecture SC-FEGAN is well suited for generating high-quality synthetic images using intuitive user inputs.
KSP 제안 키워드
Convolutional networks, End to End(E2E), End-to-end trainable, Face editing, Free-form, High-quality, Image editing, Network Architecture, User input, generative adversarial network, synthetic images