For natural image matting, context information plays a crucial role in estimating alpha mattes especially when it is challenging to distinguish foreground from its background. Exiting deep learning-based methods exploit specifically designed context aggregation modules to refine encoder features. However, the effectiveness of these modules has not been thoroughly explored. In this paper, we conduct extensive experiments to reveal that the context aggregation modules are actually not as effective as expected. We also demonstrate that when learned on large image patches, basic encoder-decoder networks with a larger receptive field can effectively aggregate context to achieve better performance.Upon the above findings, we propose a simple yet effective matting network, named AEMatter, which enlarges the receptive field by incorporating an appearance-enhanced axis-wise learning block into the encoder and adopting a hybrid-transformer decoder. Experimental results on four datasets demonstrate that our AEMatter significantly outperforms state-of-the-art matting methods (e.g., on the Adobe Composition-1K dataset, \textbf{25\%} and \textbf{40\%} reduction in terms of SAD and MSE, respectively, compared against MatteFormer). The code and model are available at \url{https://github.com/QLYoo/AEMatter}.

翻译：在自然图像抠图中，上下文信息在估计alpha遮罩时起着关键作用，特别是在区分前景与背景具有挑战性的情况下。现有的深度学习方法利用专门设计的上下文聚合模块来优化编码器特征。然而，这些模块的有效性尚未得到充分探索。本文通过大量实验揭示，上下文聚合模块实际上并不如预期那样有效。我们还证明，当在大图像块上进行训练时，具有更大感受野的基本编码器-解码器网络能够有效聚合上下文，从而实现更优性能。基于上述发现，我们提出一种简单而有效的抠图网络，命名为AEMatter，该网络通过将外观增强的轴向导学习模块融入编码器，并采用混合变换解码器来扩大感受野。在四个数据集上的实验结果表明，我们的AEMatter显著优于最先进的抠图方法（例如，在Adobe Composition-1K数据集上，与MatteFormer相比，SAD和MSE分别降低了\textbf{25\%}和\textbf{40\%}）。代码和模型可在\url{https://github.com/QLYoo/AEMatter}获取。