Fine-grained facial expression editing has long been limited by intrinsic semantic overlap. To address this, we construct the Flex Facial Expression (FFE) dataset with continuous affective annotations and establish FFE-Bench to evaluate structural confusion, editing accuracy, linear controllability, and the trade-off between expression editing and identity preservation. We propose 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 robust identity preservation, confirming its effectiveness for continuous, controllable, and fine-grained expression editing, while naturally supporting smooth expression blending.

翻译：细粒度面部表情编辑长期以来受到内在语义重叠的制约。为解决这一问题，我们构建了带有连续情感标注的Flex Facial Expression（FFE）数据集，并建立了FFE-Bench评估框架，用于衡量结构混淆、编辑精度、线性可控性以及表情编辑与身份保持之间的权衡。我们提出PixelSmile扩散框架，通过完全对称的联合训练解耦表情语义。PixelSmile融合强度监督与对比学习，生成更强且可区分性更高的表情，并通过文本潜在空间插值实现精确稳定的线性表情控制。大量实验表明，PixelSmile在解耦性能与鲁棒身份保持方面表现优异，验证了其在连续、可控、细粒度表情编辑中的有效性，同时自然支持平滑的表情融合。