Towards Natural Image Matting in the Wild via Real-Scenario Prior

TL;DR

This paper introduces COCO-Matting, a large real-world dataset for natural image matting, and proposes SEMat, a novel architecture that leverages pre-trained SAM features for improved matting performance in complex scenes.

Contribution

The paper presents a new real-world dataset COCO-Matting and a transformer-based network SEMat that enhances feature extraction and training objectives for natural image matting.

Findings

COCO-Matting contains 38,251 complex natural scene alpha mattes.

SEMat outperforms existing methods across seven diverse datasets.

The approach effectively generalizes to complex and occlusion scenes.

Abstract

Recent approaches attempt to adapt powerful interactive segmentation models, such as SAM, to interactive matting and fine-tune the models based on synthetic matting datasets. However, models trained on synthetic data fail to generalize to complex and occlusion scenes. We address this challenge by proposing a new matting dataset based on the COCO dataset, namely COCO-Matting. Specifically, the construction of our COCO-Matting includes accessory fusion and mask-to-matte, which selects real-world complex images from COCO and converts semantic segmentation masks to matting labels. The built COCO-Matting comprises an extensive collection of 38,251 human instance-level alpha mattes in complex natural scenarios. Furthermore, existing SAM-based matting methods extract intermediate features and masks from a frozen SAM and only train a lightweight matting decoder by end-to-end matting losses, which do not fully exploit the potential of the pre-trained SAM. Thus, we propose SEMat which revamps the network architecture and training objectives. For network architecture, the proposed feature-aligned transformer learns to extract fine-grained edge and transparency features. The proposed matte-aligned decoder aims to segment matting-specific objects and convert coarse masks into high-precision mattes. For training objectives, the proposed regularization and trimap loss aim to retain the prior from the pre-trained model and push the matting logits extracted from the mask decoder to contain trimap-based semantic information. Extensive experiments across seven diverse datasets demonstrate the superior performance of our method, proving its efficacy in interactive natural image matting. We open-source our code, models, and dataset at https://github.com/XiaRho/SEMat.