DiffHarmony: Latent Diffusion Model Meets Image Harmonization

arXiv:2404.06139v1 Announce Type: new
Abstract: Image harmonization, which involves adjusting the foreground of a composite image to attain a unified visual consistency with the background, can be conceptualized as an image-to-image translation task. Diffusion models have recently promoted the rapid development of image-to-image translation tasks . However, training diffusion models from scratch is computationally intensive. Fine-tuning pre-trained latent diffusion models entails dealing with the reconstruction error induced by the image compression autoencoder, making it unsuitable for image generation tasks that …

arxiv cs.cv diffusion diffusion model image type