Background matting via recursive excitation

• Main Authors: DENG, Junjie., XU, Yangyang., HE, Shengfeng., HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: image matting; recursive excitation; inference mechanisms; degradation; Computer Sciences; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8557
• Institution: Singapore Management University

We propose a simple yet effective technique that significantly improves the performance of the current state-of-the-art background matting model without compromising its original speed. We achieve this by carefully exciting the proper neural activations using an excitation map in the training phase...