The new trend of full-screen devices encourages us to position a camera behind a screen. Removing the bezel and centralizing the camera under the screen brings larger display-to-body ratio and enhances eye contact in video chat, but also causes image degradation. In this paper, we focus on a newly-defined Under-Display Camera (UDC), as a novel real-world single image restoration problem. First, we take a 4k Transparent OLED (T-OLED) and a phone Pentile OLED (P-OLED) and analyze their optical systems to understand the degradation. Second, we design a Monitor-Camera Imaging System (MCIS) for easier real pair data acquisition, and a model-based data synthesizing pipeline to generate Point Spread Function (PSF) and UDC data only from display pattern and camera measurements. Finally, we resolve the complicated degradation using deconvolution-based pipeline and learning-based methods. Our model demonstrates a real-time high-quality restoration. The presented methods and results reveal the promising research values and directions of UDC.

Liquid crystal display (LCD) technology will struggle to display high resolution on screens as big as whiteboards. Yet there is demand also for less power consumption, 3-D images, and that the display should be able to see gestures and feel touch. Most of these features are possible with projection and wedge light guides make projection slim, but picoprojectors are so dim that many will be needed for such a big screen. For now, we use instead a hybrid of technologies: light guides look out from behind an LCD to see where the viewers' hands and eyes are, and a collimated backlight lets us illuminate one view at a time to each eye. This lets us synthesize 3-D with achievable increases in LCD frame rate. We expect that this combination of a multiview 3-D display and a view-dependent rendered image will give us the potential to televise the experience of looking through a window.