CVApr 12, 2023

Adaptive Human Matting for Dynamic Videos

MicrosoftUW
arXiv:2304.06018v114 citationsh-index: 52Has Code
Originality Incremental advance
AI Analysis

This addresses the need for more adaptable and efficient video matting for real-time applications, though it appears incremental as it builds on existing trimap-free methods.

The paper tackles the problem of video matting without trimaps by introducing AdaM, a framework that improves matting realism and temporal coherence in complex real-world videos, achieving new best-in-class generalizability.

The most recent efforts in video matting have focused on eliminating trimap dependency since trimap annotations are expensive and trimap-based methods are less adaptable for real-time applications. Despite the latest tripmap-free methods showing promising results, their performance often degrades when dealing with highly diverse and unstructured videos. We address this limitation by introducing Adaptive Matting for Dynamic Videos, termed AdaM, which is a framework designed for simultaneously differentiating foregrounds from backgrounds and capturing alpha matte details of human subjects in the foreground. Two interconnected network designs are employed to achieve this goal: (1) an encoder-decoder network that produces alpha mattes and intermediate masks which are used to guide the transformer in adaptively decoding foregrounds and backgrounds, and (2) a transformer network in which long- and short-term attention combine to retain spatial and temporal contexts, facilitating the decoding of foreground details. We benchmark and study our methods on recently introduced datasets, showing that our model notably improves matting realism and temporal coherence in complex real-world videos and achieves new best-in-class generalizability. Further details and examples are available at https://github.com/microsoft/AdaM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes