PortraitGAN for Flexible Portrait Manipulation
This addresses the need for more flexible and scalable portrait manipulation tools in computer vision and graphics applications, though it appears incremental by building on existing methods like cycle-consistency.
The paper tackles the problem of discrete and single-modality facial attribute manipulation by proposing a novel framework that enables continuous and multi-modality portrait edits using adversarial learning, achieving photo-realistic effects as demonstrated in experiments.
Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality. In this paper, we propose a novel framework that supports continuous edits and multi-modality portrait manipulation using adversarial learning. Specifically, we adapt cycle-consistency into the conditional setting by leveraging additional facial landmarks information. This has two effects: first cycle mapping induces bidirectional manipulation and identity preserving; second pairing samples from different modalities can thus be utilized. To ensure high-quality synthesis, we adopt texture-loss that enforces texture consistency and multi-level adversarial supervision that facilitates gradient flow. Quantitative and qualitative experiments show the effectiveness of our framework in performing flexible and multi-modality portrait manipulation with photo-realistic effects.