# You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmaps

arXiv: https://arxiv.org/abs/2605.14166 · HTML: https://mlsanity.com/paper/2605.14166/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 31 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2308.15070/) (2023)
- [Lightweight Image Super-Resolution with Information Multi-distillation Network](https://mlsanity.com/paper/1909.11856/) (2019)
- [SRFlow: Learning the Super-Resolution Space with Normalizing Flow](https://mlsanity.com/paper/2006.14200/) (2020)
- [FSRNet: End-to-End Learning Face Super-Resolution with Facial Priors](https://mlsanity.com/paper/1711.10703/) (2017)
- [Deep Learning for Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/1808.03344/) (2018)
- [Residual Feature Distillation Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2009.11551/) (2020)
- [Progressive Face Super-Resolution via Attention to Facial Landmark](https://mlsanity.com/paper/1908.08239/) (2019)
- [Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary](https://mlsanity.com/paper/2401.08209/) (2024)
- [Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs](https://mlsanity.com/paper/1712.02765/) (2017)
- [Blueprint Separable Residual Network for Efficient Image Super-Resolution](https://mlsanity.com/paper/2205.05996/) (2022)

## Abstract (arXiv)

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 × 128 facial images from severely degraded 16 × 16 inputs, achieving an 8 ×  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.