# FoA-SR: Faithful or Aesthetic? Profile-Aware Preference Optimization for Real-World Image Super-Resolution

arXiv: https://arxiv.org/abs/2606.10275 · HTML: https://mlsanity.com/paper/2606.10275/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 26 of 26)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Designing a Practical Degradation Model for Deep Blind Image Super-Resolution](https://mlsanity.com/paper/2103.14006/) (2021)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Exploiting Diffusion Prior for Real-World Image Super-Resolution](https://mlsanity.com/paper/2305.07015/) (2023)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [MambaIR: A Simple Baseline for Image Restoration with State-Space Model](https://mlsanity.com/paper/2402.15648/) (2024)
- [SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution](https://mlsanity.com/paper/2311.16518/) (2023)
- [Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization](https://mlsanity.com/paper/2308.14469/) (2023)
- [One-Step Effective Diffusion Network for Real-World Image Super-Resolution](https://mlsanity.com/paper/2406.08177/) (2024)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution](https://mlsanity.com/paper/2411.18263/) (2024)
- [Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary](https://mlsanity.com/paper/2401.08209/) (2024)
- [DP2O-SR: Direct Perceptual Preference Optimization for Real-World Image Super-Resolution](https://mlsanity.com/paper/2510.18851/) (2025)
- [Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution](https://mlsanity.com/paper/2603.06275/) (2026)

## Abstract (arXiv)

Real-world image super-resolution (SR) is often designed with a single restoration objective, despite the current capacity of generative models to produce multiple high-quality reconstructions for the same input. In this paper, we argue that the best restoration strategy is subject to the specific restoration profile: a Faithful restoration prioritizes reference consistency, structure preservation, and hallucination suppression, whereas an Aesthetic restoration prioritizes visually pleasing and natural-looking details. We propose FoA-SR, a novel preference optimization approach to real-world SR based on profiles. To achieve this goal, FoA-SR starts with our supervised FLUX.2-based SR adapter (Flux2SR) trained with LR latent conditioning, flow matching, and image-space reconstruction losses for paired LR-to-HR image super-resolution. Following the development of the shared supervised super-resolution adapter, FoA-SR generates a shared stochastic candidate pool for each input image and ranks the same candidates using profile-specific Faithful and Aesthetic rewards to mine winner-loser pairs. These pairs are used to fine-tune separate LoRA adapters while keeping the base model frozen. Experiments on RealSR and DIV2K show that FoA-SR can steer the same SR adapter towards distinct restoration objectives: a Faithful adapter improves reference-consistent metrics while an Aesthetic adapter boosts metrics that measure perceptual quality without reference. Our candidate-pool analysis shows that Faithful and Aesthetic rewards frequently select different winners, and a Hybrid-LoRA ablation shows that collapsing both profiles into one reward yields an implicit compromise rather than explicit profile control.