FacEnhance：利用循环 DDPM 增强面部表情
FacEnhance: Facial Expression Enhancing with Recurrent DDPMs
AI总结：
本文提出 FacEnhance，一种基于循环 DDPM 的扩散方法，通过条件去噪将 64x64 低分辨率面部表情视频增强到 192x192 高分辨率，在保持身份一致性的同时补充背景细节并提升质量。
摘要：
面部表情在人类非语言交流中至关重要，已在虚拟现实、游戏和情感 AI 助手等多个计算机视觉领域得到应用。尽管已有进展，许多面部表情生成模型仍面临低分辨率（如 32x32 或 64x64 像素）、质量差以及缺乏背景细节等挑战。本文提出 FacEnhance，一种新颖的基于扩散的方法，用于解决现有低分辨率面部表情生成模型中的限制。FacEnhance 将低分辨率面部表情视频（64x64 像素）增强到更高分辨率（192x192 像素），融入背景细节并提升整体质量。该方法在扩散框架内利用条件去噪，以无背景的低分辨率视频和单张中性表情高分辨率图像为引导，生成一个视频，其中包含低分辨率视频中个体的面部表情，并采用中性图像中的背景。通过补充轻量级低分辨率模型，FacEnhance 在计算效率与理想图像分辨率和质量之间取得了平衡。在 MUG 面部表情数据库上的大量实验表明，FacEnhance 能够有效将低分辨率模型输出增强到最先进的质量，同时保持内容和身份一致性。FacEnhance 代表了向资源高效、高保真面部表情生成迈出的重要进展，使过时的低分辨率方法更新到最新标准。
英文摘要：
Facial expressions, vital in non-verbal human communication, have found applications in various computer vision fields like virtual reality, gaming, and emotional AI assistants. Despite advancements, many facial expression generation models encounter challenges such as low resolution (e.g., 32x32 or 64x64 pixels), poor quality, and the absence of background details. In this paper, we introduce FacEnhance, a novel diffusion-based approach addressing constraints in existing low-resolution facial expression generation models. FacEnhance enhances low-resolution facial expression videos (64x64 pixels) to higher resolutions (192x192 pixels), incorporating background details and improving overall quality. Leveraging conditional denoising within a diffusion framework, guided by a background-free low-resolution video and a single neutral expression high-resolution image, FacEnhance generates a video incorporating the facial expression from the low-resolution video performed by the individual with background from the neutral image. By complementing lightweight low-resolution models, FacEnhance strikes a balance between computational efficiency and desirable image resolution and quality. Extensive experiments on the MUG facial expression database demonstrate the efficacy of FacEnhance in enhancing low-resolution model outputs to state-of-the-art quality while preserving content and identity consistency. FacEnhance represents significant progress towards resource-efficient, high-fidelity facial expression generation, Renewing outdated low-resolution methods to up-to-date standards.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
