Large GAN Is All You Need

Sketch-to-portrait conversion is an emerging research area that aims to transform rough facial line sketches into highly detailed and realistic portrait images. This paper presents a comprehensive study on the impact of different loss functions and data augmentation techniques in achieving superior results using the U-Net256 network architecture. The study explores the effects of Mean Squared Error (MSE) loss, L1 loss, Generative Adversarial Network (GAN) loss, and the number of parameters on the quality of the generated portrait images. Experimental results demonstrate that the choice of loss function significantly influences the perceptual quality and accuracy of the converted portraits. While both MSE and L1 loss contribute to capturing the overall structure, GAN loss excels in generating fine-grained details. Moreover, a trade-off is observed between the number of parameters and image quality, with higher parameter counts resulting in more intricate outputs but increased computational complexity. In conclusion, this paper offers valuable insights into the sketch to portrait conversion task, shedding light on the effects of different loss functions and data augmentation techniques. The findings contribute to the advancement of sketch-to-portrait conversion systems, pushing the boundaries of realism and detail in generated portrait images. We finally reached FID value of 0.2184, the fourth in the CGI-PSG2023 leaderboard as of September 21st. The dataset can be found on CGI-PSG2023 webpage. All code is open-source and can be found in https://github.com/KKK-Liu/Portrait.git