Generative adversarial networks (GANs) have been extensively studied in the past few
years. Arguably their most significant impact has been in the area of computer vision where …

We introduce a robust, real-time, high-resolution human video matting method that achieves
new state-of-the-art performance. Our method is much lighter than previous approaches and …

We introduce a real-time, high-resolution background replacement technique which
operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU. Our technique is …

We propose a method for creating a matte-the per-pixel foreground color and alpha-of a
person by taking photos or videos in an everyday setting with a handheld camera. Most …

Existing deep learning based matting algorithms primarily resort to high-level semantic
features to improve the overall structure of alpha mattes. However, we argue that advanced …

We show that existing upsampling operators can be unified using the notion of the index
function. This notion is inspired by an observation in the decoding process of deep image …

Image matting refers to extracting precise alpha matte from natural images, and it plays a
critical role in various downstream applications, such as image editing. Despite being an ill …

Existing portrait matting methods either require auxiliary inputs that are costly to obtain or
involve multiple stages that are computationally expensive, making them less suitable for …

Over the last few years, deep learning based approaches have achieved outstanding
improvements in natural image matting. Many of these methods can generate visually …

Natural image matting separates the foreground from background in fractional occupancy
which can be caused by highly transparent objects, complex foreground (eg, net or tree) …