Authors: Dejia Xu, Yihao Chu, Qingyan Sun Description: Moiré patterns are commonly seen artifacts when taking photos of screens and other objects with high-frequency textures. It's challenging to remove the moiré patterns considering its complex color and shape. In this work, we propose an Attentive Fractal Network to effectively solve this problem. First, we construct each Attentive Fractal Block with progressive feature fusion and channel-wise attention guidance. The network is then fractally stacked with the block on each of its levels. Second, to further boost the performance, we adopt a two-stage augmented refinement strategy. With these designs, our method wins the burst demoiréing track and achieves second place in single image demoiréing and single image deblurring tracks in NTIRE20 Challenges. Extensive experiments demonstrate the superiority of our method for moiré pattern removal compared to existing state-of-the-art methods, and prove the effectiveness of its each component. We will publicly release our code and trained weights on https://github.com/ir1d/AFN.