Answers are grounded in this paper and cite their sources.
The paper-cutting style migration algorithm based on a convolutional neural network retains the characteristics of traditional paper cutting and realizes fast and accurate migration. The algorithm selects the content image as the initial, uses the small convolutional neural network to quickly extract features, introduces a new absolute error loss function to improve the image smoothness, and uses the adaptive Adam optimization algorithm to prevent the gradient problem. The experiment proves that the proposed algorithm can obtain the ideal paper-cutting style migration effect.
No takes yet. Share an insight, caveat, or question.
Ying Shang (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: