BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling

• URL: http://arxiv.org/abs/2603.01163v1
• Date: Sun, 01 Mar 2026 15:59:31 GMT
• Title: BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling
• Abstract summary: Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal.<n>Existing methods suffer from a fundamental trade-off. Supervised learning on labeled data is constrained to pixel-level label mimicry, failing to capture complex subjective human aesthetic preferences.<n>We propose BeautyGRPO, a reinforcement learning framework that aligns face retouching with human aesthetic preferences.
• Score: 29.77085426345252
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face retouching requires removing subtle imperfections while preserving unique facial identity features, in order to enhance overall aesthetic appeal. However, existing methods suffer from a fundamental trade-off. Supervised learning on labeled data is constrained to pixel-level label mimicry, failing to capture complex subjective human aesthetic preferences. Conversely, while online reinforcement learning (RL) excels at preference alignment, its stochastic exploration paradigm conflicts with the high-fidelity demands of face retouching and often introduces noticeable noise artifacts due to accumulated stochastic drift. To address these limitations, we propose BeautyGRPO, a reinforcement learning framework that aligns face retouching with human aesthetic preferences. We construct FRPref-10K, a fine-grained preference dataset covering five key retouching dimensions, and train a specialized reward model capable of evaluating subtle perceptual differences. To reconcile exploration and fidelity, we introduce Dynamic Path Guidance (DPG). DPG stabilizes the stochastic sampling trajectory by dynamically computing an anchor-based ODE path and replanning a guided trajectory at each sampling timestep, effectively correcting stochastic drift while maintaining controlled exploration. Extensive experiments show that BeautyGRPO outperforms both specialized face retouching methods and general image editing models, achieving superior texture quality, more accurate blemish removal, and overall results that better align with human aesthetic preferences.

Related papers

• PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation [54.85864545266293]
  We propose PortraitGen, a novel framework tailored for photorealistic portrait generation.<n>First, we break inherent generative boundaries by directly introducing real images into the GRPO sampling groups.<n>We introduce a complementary dual-reward mechanism: OmniReward for general quality and AI-Portrait for human-centric fidelity.
  arXiv  Detail & Related papers  (2026-06-25T12:05:40Z)
• MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation [65.068801413044]
  Continual test-time adaptation adapts a source-pretrained model to non-stationary, unlabeled target streams.<n>We introduce MoASE, a mixture-of-experts that disentangles domain-agnostic structure from domain-specific texture.
  arXiv  Detail & Related papers  (2026-05-18T01:52:12Z)
• Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping [66.25536973294726]
  Post-training methods for text-to-image (T2I) models are prone to reward hacking.<n>Super-Linear Advantage Shaping (SLAS) reshapes the local policy space.<n>SLAS consistently surpasses the DanceGRPO baseline across multiple backbones and benchmarks.
  arXiv  Detail & Related papers  (2026-05-11T17:59:25Z)
• Q-DeepSight: Incentivizing Thinking with Images for Image Quality Assessment and Refinement [58.15004031934379]
  We propose Q-DeepSight, a think-with-image framework that emulates this human-like process.<n>Q-DeepSight achieves state-of-the-art performance across diverse benchmarks, including natural, restored, and AI-generated content.<n>We demonstrate its practical value with Perceptual-in-Generation (PiG), a training-free framework where Q-DeepSight's diagnoses guide iterative image enhancement.
  arXiv  Detail & Related papers  (2026-04-18T06:10:57Z)
• Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference [69.34278282513593]
  Preference Score Distillation (PSD) is an optimization-based framework for human-aligned text-to-3D synthesis without 3D training data.<n>Our key insight stems from the incompatibility of pixel-level gradients.<n>We introduce an adaptive strategy to co-optimize preference scores and negative text embeddings.
  arXiv  Detail & Related papers  (2026-03-02T08:23:36Z)
• Synthetic Craquelure Generation for Unsupervised Painting Restoration [17.344021694835345]
  We propose a fully annotation-free framework driven by a domain-specific synthetic craquelure generator.<n>Our approach couples a classical morphological detector with a learning-based refinement module.<n>Our pipeline significantly outperforms state-of-the-art photographic restoration models in zero-shot settings.
  arXiv  Detail & Related papers  (2026-02-13T09:13:46Z)
• PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching [54.3683137773426]
  We propose a unified diffusion-based image retouching framework called PerTouch.<n>Our method supports semantic-level image retouching while maintaining global aesthetics.<n>We develop a VLM-driven agent that can handle both strong and weak user instructions.
  arXiv  Detail & Related papers  (2025-11-17T05:39:15Z)
• Finetuning-Free Personalization of Text to Image Generation via Hypernetworks [15.129799519953139]
  We introduce fine-tuning-free personalization via Hypernetworks that predict LoRA-adapted weights directly from subject images.<n>Our approach achieves strong personalization performance and highlights the promise of hypernetworks as a scalable and effective direction for open-category personalization.
  arXiv  Detail & Related papers  (2025-11-05T03:31:33Z)
• Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization [63.169050703903515]
  We propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL)<n>Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data.<n>Experiments demonstrate that Aes-R1 improves the backbone's average PLCC/SRCC by 47.9%/34.8%.
  arXiv  Detail & Related papers  (2025-09-26T04:55:00Z)
• Bi-Level Optimization for Self-Supervised AI-Generated Face Detection [56.57881725223548]
  We introduce a self-supervised method for AI-generated face detectors based on bi-level optimization.<n>Our detectors significantly outperform existing approaches in both one-class and binary classification settings.
  arXiv  Detail & Related papers  (2025-07-30T16:38:29Z)
• DynFaceRestore: Balancing Fidelity and Quality in Diffusion-Guided Blind Face Restoration with Dynamic Blur-Level Mapping and Guidance [29.961208234237635]
  Blind Face Restoration aims to recover high-fidelity, detail-rich facial images from unknown degraded inputs.<n>We propose DynFaceRestore, a novel blind face restoration approach that learns to map any blindly degraded input to blurry images.<n>DynFaceRestore achieves state-of-the-art performance in both quantitative and qualitative evaluations.
  arXiv  Detail & Related papers  (2025-07-18T10:16:08Z)
• Joint angle model based learning to refine kinematic human pose estimation [8.6527127612359]
  Current human pose estimation (HPE) suffers from occasional errors in keypoint recognition and random fluctuation in keypoint trajectories.<n>This paper proposed a method to overcome the difficulty through joint angle-based modeling.<n>A bidirectional recurrent network is designed as a post-processing module to refine the estimation of well-established HRNet.
  arXiv  Detail & Related papers  (2025-07-15T08:16:39Z)
• RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection [25.08843970102635]
  We introduce RetouchingFFHQ, a large-scale and fine-grained face retouching dataset. By including four typical types of face retouching operations and different retouching levels, we extend the binary face retouching detection into a fine-grained, multi-retouching type, and multi-retouching level estimation problem.
  arXiv  Detail & Related papers  (2023-07-20T07:12:56Z)
• Towards Robust Blind Face Restoration with Codebook Lookup Transformer [94.48731935629066]
  Blind face restoration is a highly ill-posed problem that often requires auxiliary guidance. We show that a learned discrete codebook prior in a small proxy space cast blind face restoration as a code prediction task. We propose a Transformer-based prediction network, named CodeFormer, to model global composition and context of the low-quality faces.
  arXiv  Detail & Related papers  (2022-06-22T17:58:01Z)
• SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition [74.13631562652836]
  We propose a novel loss function, named sigmoid-constrained hypersphere loss (SFace) SFace imposes intra-class and inter-class constraints on a hypersphere manifold, which are controlled by two sigmoid gradient re-scale functions respectively. It can make a better balance between decreasing the intra-class distances and preventing overfitting to the label noise, and contributes more robust deep face recognition models.
  arXiv  Detail & Related papers  (2022-05-24T11:54:15Z)

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.