ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer

TL;DR

This paper presents a novel one-stage face re-aging method that combines portrait style transfer for non-photorealistic images, enabling seamless editing of apparent age while preserving style and facial attributes.

Contribution

Introduces a unified generative approach for face re-aging and style transfer in non-photorealistic images, eliminating the need for domain-specific fine-tuning or paired datasets.

Findings

Effective in generating re-aged images with style transfer in a single step

Maintains facial attributes and natural appearance in stylized re-aging

Flexible exemplar-based approach surpasses domain-level fine-tuning limitations

Abstract

Face re-aging is a prominent field in computer vision and graphics, with significant applications in photorealistic domains such as movies, advertising, and live streaming. Recently, the need to apply face re-aging to non-photorealistic images, like comics, illustrations, and animations, has emerged as an extension in various entertainment sectors. However, the lack of a network that can seamlessly edit the apparent age in NPR images has limited these tasks to a naive, sequential approach. This often results in unpleasant artifacts and a loss of facial attributes due to domain discrepancies. In this paper, we introduce a novel one-stage method for face re-aging combined with portrait style transfer, executed in a single generative step. We leverage existing face re-aging and style transfer networks, both trained within the same PR domain. Our method uniquely fuses distinct latent vectors, each responsible for managing aging-related attributes and NPR appearance. By adopting an exemplar-based approach, our method offers greater flexibility compared to domain-level fine-tuning approaches, which typically require separate training or fine-tuning for each domain. This effectively addresses the limitation of requiring paired datasets for re-aging and domain-level, data-driven approaches for stylization. Our experiments show that our model can effortlessly generate re-aged images while simultaneously transferring the style of examples, maintaining both natural appearance and controllability.