你只需一次地标：基于YOLO-World地标热图的轻量级U-Net人脸超分辨率
You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmaps
AI总结：
提出轻量级U-Net，利用YOLO-World生成的地标热图作为监督，无需额外训练辅助网络，实现8倍人脸超分辨率重建，提升关键区域细节。
摘要：
人脸图像超分辨率旨在从严重退化的输入中恢复高分辨率人脸图像。在极端放大因子下，精细的面部细节常常丢失，使得准确重建具有挑战性。现有方法通常依赖重型网络架构、对抗训练方案或单独的对齐网络，增加了模型复杂度和计算成本。为解决这些问题，我们提出了一种基于轻量级U-Net的架构，旨在从严重退化的$16 \ imes 16$输入重建$128 \ imes 128$面部图像，实现$8 \ imes$放大。一个关键贡献是一种新颖的无辅助训练监督策略，利用YOLO-World（一种开放词汇目标检测器）生成的热图来定位关键面部特征，如眼睛、鼻子和嘴巴。这些热图被转换为空间权重，形成热图引导的损失，强调语义重要区域的重建误差。与先前需要专用地标或对齐网络的方法不同，我们的方法直接重用检测器输出作为监督，保持高效的训练和推理流程。在对齐的CelebA数据集上的实验表明，所提出的损失一致地改善了定量指标，并产生了更清晰、更逼真的重建。总体而言，我们的结果表明，轻量级网络可以有效地利用检测驱动的先验进行感知上令人信服的极端放大，而无需对抗训练或增加计算成本。
英文摘要：
Face image super-resolution aims to recover high-resolution facial images from severely degraded inputs. Under extreme upscaling factors, fine facial details are often lost, making accurate reconstruction challenging. Existing methods typically rely on heavy network architectures, adversarial training schemes, or separate alignment networks, increasing model complexity and computational cost. To address these issues, we propose a lightweight U-Net based-architecture designed to reconstructs $128{ \times }128$ facial images from severely degraded $16{ \times }16$ inputs, achieving an $8 \times $ magnification. A key contribution is a novel auxiliary-training-free supervision strategy that leverages heatmaps generated by YOLO-World, an open-vocabulary object detector, to localize key facial features such as eyes, nose, and mouth. These heatmaps are converted into spatial weights to form a heatmap-guided loss that emphasizes reconstruction errors in semantically important regions. Unlike prior methods that require dedicated landmark or alignment networks, our approach directly reuses detector outputs as supervision, maintaining an efficient training and inference pipeline. Experiments on the aligned CelebA dataset demonstrate that the proposed loss consistently improves quantitative metrics and produces sharper, more realistic reconstructions. Overall, our results show that lightweight networks can effectively exploit detection-driven priors for perceptually convincing extreme upscaling, without adversarial training or increased computational cost.
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。
