OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution

• URL: http://arxiv.org/abs/2603.12811v1
• Date: Fri, 13 Mar 2026 09:12:46 GMT
• Title: OARS: Process-Aware Online Alignment for Generative Real-World Image Super-Resolution
• Abstract summary: OARS is a process-aware online alignment framework that evaluates the LR to SR transition by jointly modeling fidelity preservation and perceptual gain.<n>We show consistent perceptual improvements while maintaining fidelity, achieving state-of-the-art performance on Real-ISR benchmarks.
• Score: 47.35253230699505
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aligning generative real-world image super-resolution models with human visual preference is challenging due to the perception--fidelity trade-off and diverse, unknown degradations. Prior approaches rely on offline preference optimization and static metric aggregation, which are often non-interpretable and prone to pseudo-diversity under strong conditioning. We propose OARS, a process-aware online alignment framework built on COMPASS, a MLLM-based reward that evaluates the LR to SR transition by jointly modeling fidelity preservation and perceptual gain with an input-quality-adaptive trade-off. To train COMPASS, we curate COMPASS-20K spanning synthetic and real degradations, and introduce a three-stage perceptual annotation pipeline that yields calibrated, fine-grained training labels. Guided by COMPASS, OARS performs progressive online alignment from cold-start flow matching to full-reference and finally reference-free RL via shallow LoRA optimization for on-policy exploration. Extensive experiments and user studies demonstrate consistent perceptual improvements while maintaining fidelity, achieving state-of-the-art performance on Real-ISR benchmarks.

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• Improving Visual Representation Alignment Generation with GRPO [51.071351994330605]
  diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment.<n>We propose VRPO, a reinforcement-based optimization strategy that replaces REPA's static alignment loss with a generative representation policy optimization objective.<n>Our VRPO-driven training seamlessly integrates into diffusion transformers, introducing negligible cost and preserving full compatibility with SiT and DiT architectures.
  arXiv  Detail & Related papers  (2026-05-30T07:21:40Z)
• Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models [58.3184497327891]
  Distilled autoregressive (AR) video models enable efficient streaming generation but frequently misalign with human visual preferences.<n>We present Astrolabe, an efficient online reinforcement learning framework tailored for distilled AR models.
  arXiv  Detail & Related papers  (2026-03-17T18:32:18Z)
• LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Generative Real-World Super-Resolution [21.290660354883595]
  Preference-based reinforcement learning (RL) is a natural fit because each LR input yields a rollout group of candidates to compare.<n>We propose LucidNFT, a multi-reward RL framework for flow-matching Real-ISR.<n>Experiments show that LucidNFT consistently improves strong flow-based Real-ISR baselines.
  arXiv  Detail & Related papers  (2026-03-06T06:30:34Z)
• Bidirectional Reward-Guided Diffusion for Real-World Image Super-Resolution [79.35296000454694]
  Diffusion-based super-resolution can synthesize rich details, but models trained on synthetic paired data often fail on real-world LR images.<n>We propose Bird-SR, a reward-guided diffusion framework that formulates super-resolution as trajectory-level preference optimization.<n>Experiments on real-world SR benchmarks demonstrate that Bird-SR consistently outperforms state-of-the-art methods in perceptual quality.
  arXiv  Detail & Related papers  (2026-02-05T19:21:45Z)
• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• Adaptive Replay Buffer for Offline-to-Online Reinforcement Learning [29.513882808306406]
  We introduce the Adaptive Replay Buffer (ARB), a novel approach that prioritizes data sampling based on a lightweight metric we call 'on-policyness'<n>ARB is designed to be learning-free and simple to implement, seamlessly integrating into existing Offline-to-Online Reinforcement Learning algorithms.<n>Our experiments on D4RL benchmarks demonstrate that ARB consistently mitigates early performance degradation and significantly improves the final performance of various O2O RL algorithms.
  arXiv  Detail & Related papers  (2025-12-11T10:30:04Z)
• Dual-domain Adaptation Networks for Realistic Image Super-resolution [81.34345637776408]
  Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones.<n>Current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features.<n>We introduce a novel approach, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets.
  arXiv  Detail & Related papers  (2025-11-21T12:57:23Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Realism Control One-step Diffusion for Real-World Image Super-Resolution [21.13930153613271]
  We propose a Realism Controlled One-step Diffusion (RCOD) framework for Real-ISR.<n>RCOD provides explicit control over fidelity-realism trade-offs during the noise prediction phase.<n>Our method achieves superior fidelity and perceptual quality while maintaining computational efficiency.
  arXiv  Detail & Related papers  (2025-09-12T10:32:04Z)
• Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL [40.05960121330012]
  Online reinforcement learning (RL) with complex function approximations plays a significant role in the modern practice of artificial intelligence.<n> balancing the fundamental trade-off between exploration and exploitation remains a long-standing challenge.<n>This paper provides an interpretation of the principle of optimism through the lens of primal-dual optimization.
  arXiv  Detail & Related papers  (2025-06-27T17:18:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.