You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmaps
For practitioners needing efficient face super-resolution, this work offers a lightweight alternative that avoids complex adversarial training or separate alignment networks, though the improvement is incremental over existing methods.
This paper proposes a lightweight U-Net for 8x face super-resolution (16x16 to 128x128) that uses YOLO-World heatmaps as a novel auxiliary-training-free supervision strategy, achieving sharper reconstructions without adversarial training. On CelebA, the heatmap-guided loss consistently improves quantitative metrics.
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.