RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation

• URL: http://arxiv.org/abs/2608.29280v1
• Date: Sat, 29 Aug 2026 14:06:09 GMT
• Title: RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation
• Abstract summary: Reinforcement Learning can reshape the sampling distribution of flow models.<n>Garment-RM trained on 500K images via fine-grained contrastive learning, achieving 84.67% human preference accuracy.<n>Our strategy integrates a dynamic discriminator into the RL sampling trajectory to penalize artifacts while enriching authentic high-frequency details.
• Score: 41.42598259381642
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Standard clothing asset generation---restoring forward-facing flat-lay garment images from diverse real-world contexts---holds immense commercial value yet demands both macroscopic topological accuracy and microscopic physical fidelity. Although our previous work RAGDiffusion effectively eradicated large-scale structural hallucinations via retrieval-augmented macro-constraints, achieving industrial-grade micro-texture realism remains an unsolved bottleneck. We formally identify this limitation as High-Frequency Trajectory Collapse: supervised fine-tuning (SFT) converges to the conditional mean of the training distribution, which is dominated by smooth, low-frequency textures, causing high-frequency patterns (e.g., fabric weaves, intricate logos) to become nearly un-sampleable. Naively applying Reinforcement Learning (RL) post-training further triggers Artifact Hacking, where models exploit semantic biases in generic reward models by generating deceptive checkerboard noise. Our key insight is that RL can fundamentally reshape the sampling distribution of flow models---elevating the probability of high-fidelity trajectories under accurate reward guidance---while adversarial regularization prevents exploitation of reward blind spots. Realizing this principle requires three prerequisites: (i)inherent capacity, established through a 27,725-pair high-complexity garment dataset (STGarment-Plus) and a Dual-Image-Stream FLUX architecture upgrade; (ii)perceptive reward, provided by a novel attribute-aware reward model (Garment-RM) trained on 500K images via fine-grained contrastive learning, achieving 84.67% human preference accuracy; and (iii)hacking prevention, enforced by our Adversarial-Regularized GRPO (AR-GRPO) strategy that integrates a dynamic discriminator into the RL sampling trajectory to penalize artifacts while enriching authentic high-frequency details.

Related papers

• FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration [3.7323617838648566]
  Flow-Conditioned Detail Refinement (FCDR) deterministically restores high-frequency textures and suppresses generative hallucinations in pixel space.<n>FDIR achieves superior fidelity, with a favorable perceptual-fidelity balance and competitive machine preference.
  arXiv  Detail & Related papers  (2026-07-31T08:33:40Z)
• IB-Flow: Information Bottleneck-Guided CFG Distillation for Few-Step Text-to-Image Generation [9.17007090517294]
  Few-step distillation targeting the Free Guidance trajectory has emerged as the prevalent dual-dimensional compression paradigm.<n>We re-examine the distillation procedure through the theoretical lens of Information Theory.<n>We propose an instance-aware selection mechanism that transmutes the intractable KL divergence constraint into a zero-overhead closed-form solution.
  arXiv  Detail & Related papers  (2026-07-10T06:43:43Z)
• Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps [54.68389949880821]
  We propose GaussLock, a framework to defend 3D generative models against fine-tuning attacks.<n>GassLock integrates authorized distillation with attribute-aware trap losses targeting position, scale, rotation, opacity, and color.<n>Experiments show that GaussLock effectively neutralizes unauthorized fine-tuning attacks.
  arXiv  Detail & Related papers  (2026-04-06T09:30:49Z)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models [15.709482146201283]
  A simple linear classifier trained on the frozen features of modern Vision Foundation Models establishes a new state-of-the-art.<n>We show that this baseline matches specialized detectors on standard benchmarks but also decisively outperforms them on in-the-wild datasets.<n>We conclude by advocating for a paradigm shift in AI forensics, moving from overfitting on static benchmarks to harnessing the evolving world knowledge of foundation models for real-world reliability.
  arXiv  Detail & Related papers  (2026-02-02T07:20:02Z)
• Smooth Operator: Smooth Verifiable Reward Activates Spatial Reasoning Ability of Vision-Language Model [18.526821056010384]
  Vision-Language Models (VLMs) face a critical bottleneck in achieving precise numerical prediction for 3D scene understanding.<n>Traditional reinforcement learning approaches, primarily based on relative ranking, often suffer from severe reward sparsity and gradient instability.<n>We introduce the Smooth Numerical Reward Activation (SNRA) operator and the Absolute-Preserving GRPO framework.
  arXiv  Detail & Related papers  (2026-01-12T16:26:42Z)
• Restoration Score Distillation: From Corrupted Diffusion Pretraining to One-Step High-Quality Generation [82.39763984380625]
  We propose textitRestoration Score Distillation (RSD), a principled generalization of Denoising Score Distillation (DSD)<n>RSD accommodates a broader range of corruption types, such as blurred, incomplete, or low-resolution images.<n>It consistently surpasses its teacher model across diverse restoration tasks on both natural and scientific datasets.
  arXiv  Detail & Related papers  (2025-05-19T17:21:03Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• Soft ascent-descent as a stable and flexible alternative to flooding [6.527016551650139]
  We propose a softened, pointwise mechanism called SoftAD that downweights points on the borderline, limits the effects of outliers, and retains the ascent-descent effect of flooding. We demonstrate how SoftAD can realize classification accuracy competitive with flooding while enjoying a much smaller loss generalization gap and model norm.
  arXiv  Detail & Related papers  (2023-10-16T02:02:56Z)
• Exploiting Diffusion Prior for Real-World Image Super-Resolution [75.5898357277047]
  We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution. By employing our time-aware encoder, we can achieve promising restoration results without altering the pre-trained synthesis model.
  arXiv  Detail & Related papers  (2023-05-11T17:55:25Z)

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.