PixelSmile: Toward Fine-Grained Facial Expression Editing

Fine-grained facial expression editing is limited by intrinsic semantic overlap. To address this, we construct the $\text{Flex Facial Expression}$ (FFE) dataset with continuous affective annotations and establish $\text{FFE-Bench}$ to evaluate structural confusion, editing accuracy, linear controllability, and the trade-off between expression editing and identity preservation. We propose $\text{PixelSmile}$, a diffusion framework that disentangles expression semantics via fully symmetric joint training. PixelSmile combines intensity supervision with contrastive learning to produce stronger and more distinguishable expressions, achieving precise and stable linear expression control through textual latent interpolation. Extensive experiments demonstrate that PixelSmile achieves superior disentanglement and identity preservation, enabling fine-grained continuous expression editing and smooth expression blending.