Toward Real-World High-Precision Image Matting and Segmentation

TL;DR

This paper introduces FCLM, a novel model for high-precision image matting and segmentation that leverages depth-aware distillation, domain-invariant learning, and an object-oriented decoder to improve real-world performance and generalization.

Contribution

The paper proposes FCLM, integrating depth-aware distillation, domain-invariant learning, and an object-oriented decoder for enhanced scene parsing and interactive segmentation.

Findings

Outperforms state-of-the-art methods quantitatively.

Achieves superior qualitative segmentation results.

Effectively generalizes to real-world scenarios.

Abstract

High-precision scene parsing tasks, including image matting and dichotomous segmentation, aim to accurately predict masks with extremely fine details (such as hair). Most existing methods focus on salient, single foreground objects. While interactive methods allow for target adjustment, their class-agnostic design restricts generalization across different categories. Furthermore, the scarcity of high-quality annotation has led to a reliance on inharmonious synthetic data, resulting in poor generalization to real-world scenarios. To this end, we propose a Foreground Consistent Learning model, dubbed as FCLM, to address the aforementioned issues. Specifically, we first introduce a Depth-Aware Distillation strategy where we transfer the depth-related knowledge for better foreground representation. Considering the data dilemma, we term the processing of synthetic data as domain adaptation problem where we propose a domain-invariant learning strategy to focus on foreground learning. To support interactive prediction, we contribute an Object-Oriented Decoder that can receive both visual and language prompts to predict the referring target. Experimental results show that our method quantitatively and qualitatively outperforms SOTA methods.