• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.877-893
• /
• 2022

With the development of deep learning, face inpainting has been significantly enhanced in the past few years. Although image inpainting framework integrated with generative adversarial network or attention mechanism enhanced the semantic understanding among facial components, the issues of reconstruction on corrupted regions are still worthy to explore, such as blurred edge structure, excessive smoothness, unreasonable semantic understanding and visual artifacts, etc. To address these issues, we propose a Learnable Structure Knowledge of Fusion Network (LSK-FNet), which learns a prior knowledge by edge generation network for image inpainting. The architecture involves two steps: Firstly, structure information obtained by edge generation network is used as the prior knowledge for face inpainting network. Secondly, both the generated prior knowledge and the incomplete image are fed into the face inpainting network together to get the fusion information. To improve the accuracy of inpainting, both of gated convolution and region normalization are applied in our proposed model. We evaluate our LSK-FNet qualitatively and quantitatively on the CelebA-HQ dataset. The experimental results demonstrate that the edge structure and details of facial images can be improved by using LSK-FNet. Our model surpasses the compared models on L1, PSNR and SSIM metrics. When the masked region is less than 20%, L1 loss reduce by more than 4.3%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권3호
• /
• pp.881-895
• /
• 2023

Modern image inpainting techniques based on deep learning have achieved remarkable performance, and more and more people are working on repairing more complex and larger missing areas, although this is still challenging, especially for facial image inpainting. For a face image with a huge missing area, there are very few valid pixels available; however, people have an ability to imagine the complete picture in their mind according to their subjective will. It is important to simulate this capability while maintaining the identity features of the face as much as possible. To achieve this goal, we propose a three-stage network model, which we refer to as the identity and structure feature refinement network (ISFRNet). ISFRNet is based on 1) a pre-trained pSp-styleGAN model that generates an extremely realistic face image with rich structural features; 2) a shallow structured network with a small receptive field; and 3) a modified U-net with two encoders and a decoder, which has a large receptive field. We choose structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), L1 Loss and learned perceptual image patch similarity (LPIPS) to evaluate our model. When the missing region is 20%-40%, the above four metric scores of our model are 28.12, 0.942, 0.015 and 0.090, respectively. When the lost area is between 40% and 60%, the metric scores are 23.31, 0.840, 0.053 and 0.177, respectively. Our inpainting network not only guarantees excellent face identity feature recovery but also exhibits state-of-the-art performance compared to other multi-stage refinement models.

• 한국정보통신학회논문지
• /
• 제17권1호
• /
• pp.15-31
• /
• 2013

본 논문은 최근 관심이 고조되고 있는 디지털 홀로그램의 시야각을 확보하기 위하여 시청자의 시점을 추적하여 그 시점에 해당하는 데이터를 생성하고, 이를 디지털 홀로그램으로 변환하는 방법을 제안한다. 이 방법은 제어하는 시야각의 맨 좌측과 맨 우측 시점에 대한 정보(깊이정보와 컬러 또는 명도정보)가 주어졌다고 가정한다. 이 방법은 주어진 좌, 우측의 깊이영상을 대상으로 스테레오 정합에 의해 단위 깊이 당 의사변위증분을 구하여 사용한다. 이를 이용하여 주어진 좌, 우측시점으로부터 원하는 가상시점의 정보를 생성하고, 그 결과의 두 영상을 결합하여 해당시점의 정보를 획득한다. 이 경우 발생하는 비폐색 영역을 정의하고 이를 채우는 방법을 제안한다. 이 방법을 구현하여 실험한 결과 생성한 중간 시점의 깊이영상과 RGB영상의 평균 화질은 각각 33.83[dB]과 29.5[dB]이었으며, 평균 수행속도는 프레임 당 250[ms]이었다. 또한 이 방법을 이용하여 시청자와 인터랙티브하게 디지털 홀로그램을 서비스하는 시스템의 프로토타입을 제안한다. 이 시스템에는 좌, 우 시점의 영상정보를 획득, 카메라 캘리브래이션과 영상보정, 중간시점 영상생성, 컴퓨터-생성홀로그램(computer-generated hologram, CGH) 생성 및 홀로그램 영상복원기능을 포함한다. 이 시스템은 LabView(R) 환경에서 구현되며, CGH생성과 홀로그램 영상 복원은 GPGPU로, 나머지는 소프트웨어로 구현한다. 구현결과 평균 수행 속도는 초당 약 5 프레임을 처리할 수 있는 속도이었다.