Towards Flexible, Scalable, and Adaptive Multi-Modal Conditioned Face Synthesis

TL;DR

This paper introduces a novel multi-modal face synthesis method that enhances flexibility, scalability, and control by using uni-modal training with modal surrogates and entropy-aware modulation, leading to higher quality results.

Contribution

The paper proposes a uni-modal training approach with modal surrogates and entropy-aware modulation for improved multi-modal face synthesis.

Findings

Outperforms existing methods in image quality and fidelity

Supports flexible and scalable multi-modal control

Achieves high-fidelity face synthesis results

Abstract

Recent progress in multi-modal conditioned face synthesis has enabled the creation of visually striking and accurately aligned facial images. Yet, current methods still face issues with scalability, limited flexibility, and a one-size-fits-all approach to control strength, not accounting for the differing levels of conditional entropy, a measure of unpredictability in data given some condition, across modalities. To address these challenges, we introduce a novel uni-modal training approach with modal surrogates, coupled with an entropy-aware modal-adaptive modulation, to support flexible, scalable, and scalable multi-modal conditioned face synthesis network. Our uni-modal training with modal surrogate that only leverage uni-modal data, use modal surrogate to decorate condition with modal-specific characteristic and serve as linker for inter-modal collaboration , fully learns each modality control in face synthesis process as well as inter-modal collaboration. The entropy-aware modal-adaptive modulation finely adjust diffusion noise according to modal-specific characteristics and given conditions, enabling well-informed step along denoising trajectory and ultimately leading to synthesis results of high fidelity and quality. Our framework improves multi-modal face synthesis under various conditions, surpassing current methods in image quality and fidelity, as demonstrated by our thorough experimental results.