Official repository for the paper Real-Time High-Resolution Background Matting. Our model requires capturing an additional background image and produces state-of-the-art matting results at 4K 30fps ...
Abstract: Capsule networks (CapsNet) are a pioneering architecture that can encode image features into vectors rather than scalars, addressing the limitations of traditional Convolutional Neural ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results