Learning Trimaps via Clicks for Image Matting

TL;DR

This paper introduces Click2Trimap, an interactive model that predicts high-quality trimaps and alpha mattes with minimal user clicks, significantly reducing user effort and time in image matting tasks.

Contribution

The paper presents a novel interactive approach with an iterative training strategy and simulation function, enabling efficient trimap prediction with minimal user input.

Findings

Outperforms existing trimap-free matting methods in accuracy.

Achieves high-quality trimaps and mattes in about 5 seconds per image.

Demonstrates practical value in real-world applications.

Abstract

Despite significant advancements in image matting, existing models heavily depend on manually-drawn trimaps for accurate results in natural image scenarios. However, the process of obtaining trimaps is time-consuming, lacking user-friendliness and device compatibility. This reliance greatly limits the practical application of all trimap-based matting methods. To address this issue, we introduce Click2Trimap, an interactive model capable of predicting high-quality trimaps and alpha mattes with minimal user click inputs. Through analyzing real users' behavioral logic and characteristics of trimaps, we successfully propose a powerful iterative three-class training strategy and a dedicated simulation function, making Click2Trimap exhibit versatility across various scenarios. Quantitative and qualitative assessments on synthetic and real-world matting datasets demonstrate Click2Trimap's superior performance compared to all existing trimap-free matting methods. Especially, in the user study, Click2Trimap achieves high-quality trimap and matting predictions in just an average of 5 seconds per image, demonstrating its substantial practical value in real-world applications.