像素微笑：迈向精细化面部表情编辑

摘要

细粒度面部表情编辑长期受限于内在语义重叠问题。为解决这一难题，我们构建了带有连续情感标注的FFE数据集，并建立FFE-Bench评估框架，从结构混淆度、编辑精度、线性可控性以及表情编辑与身份保持的平衡性等维度进行系统评估。我们提出PixelSmile扩散框架，通过完全对称的联合训练实现表情语义解耦。该框架将强度监督与对比学习相结合，生成更具表现力且可区分度更高的表情，借助文本隐空间插值实现精准稳定的线性表情控制。大量实验表明，PixelSmile在解耦效果和身份特征保持方面表现优异，证实了其在连续可控的细粒度表情编辑方面的有效性，同时天然支持平滑的表情融合效果。

English

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.

像素微笑：迈向精细化面部表情编辑

PixelSmile: Toward Fine-Grained Facial Expression Editing

摘要

Support