Pith. sign in

Revisiting Context Aggregation for Image Matting

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Traditional studies emphasize the significance of context information in improving matting performance. Consequently, deep learning-based matting methods delve into designing pooling or affinity-based context aggregation modules to achieve superior results. However, these modules cannot well handle the context scale shift caused by the difference in image size during training and inference, resulting in matting performance degradation. In this paper, we revisit the context aggregation mechanisms of matting networks and find that a basic encoder-decoder network without any context aggregation modules can actually learn more universal context aggregation, thereby achieving higher matting performance compared to existing methods. Building on this insight, we present AEMatter, a matting network that is straightforward yet very effective. AEMatter adopts a Hybrid-Transformer backbone with appearance-enhanced axis-wise learning (AEAL) blocks to build a basic network with strong context aggregation learning capability. Furthermore, AEMatter leverages a large image training strategy to assist the network in learning context aggregation from data. Extensive experiments on five popular matting datasets demonstrate that the proposed AEMatter outperforms state-of-the-art matting methods by a large margin.

citation-role summary

background 1

citation-polarity summary

fields

cs.CV 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.

  • Uncertainty-Guided Face Matting for Occlusion-Aware Face Transformation cs.CV · 2025-08-05 · conditional · none · ref 21 · internal anchor

    A two-stage, uncertainty-guided knowledge distillation method for trimap-free face matting, along with a new synthetic occlusion dataset, modestly outperforms existing matting baselines on face-focused benchmarks.