In this paper we propose the Matting Anything Model (MAM) an efficient and versatile
framework for estimating the alpha matte of any instance in an image with flexible and …

Video matting aims to predict the alpha mattes for each frame from a given input video
sequence. Recent solutions to video matting have been dominated by deep convolutional …

Conventional video matting outputs one alpha matte for all instances appearing in a video
frame so that individual instances are not distinguished. While video instance segmentation …

Virtual production, a filmmaking technique that seamlessly merges virtual and real
cinematography, has revolutionized the film and television industry. However, traditional …

In order to enhance the matting performance in multi-person dynamic scenarios, we
introduce a robust, real-time, high-resolution, and controllable human video matting method …

Real-time video matting is essential for applications like online video conferencing but faces
challenges in human-object interaction (HOI) scenarios, known as the HOI-matting problem …

Video portrait segmentation is essential for intelligent sensing systems, including human-
computer interaction, autonomous navigation, and augmented reality. However, dynamic …

Video matting is a technique used to replace foreground objects in video frames by
predicting their alpha matte. Originally developed for film special effects, advertisements …

High-quality animated stickers usually contain transparent channels, which are often
ignored by current video generation models. To generate fine-grained animated …

Video matting and video instance segmentation cannot distinguish alpha mattes in a
scenario featuring multiple instances. We propose a video instance matting method guided …