DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation

• URL: http://arxiv.org/abs/2607.02220v1
• Date: Thu, 02 Jul 2026 14:26:47 GMT
• Title: DetailAnywhere: Fashion Detail Generation via Cross-Modal Feature Alignment Distillation
• Abstract summary: Diffusion-based generative AI has achieved remarkable success in e-commerce applications such as virtual try-on, poster generation, and product background synthesis.<n>We formalize a new non-template task: Fashion Detail Generation with focus conditioning, and release FDBench.<n> FDBench is the first benchmark comprising 40K+ human-verified reference-detail pairs across 41 different categories.
• Score: 13.86318416278238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion-based generative AI has achieved remarkable success in e-commerce applications such as virtual try-on, poster generation, and product background synthesis. However, when making online purchasing decisions for apparel, consumers also desire the freedom to examine specific detail regions of interest, such as collars, cuffs, and fabric textures, yet existing methods have not explicitly studied this setting. We therefore formalize a new, non-template task: Fashion Detail Generation with focus conditioning, and release FDBench, the first benchmark comprising 40K+ human-verified reference-detail pairs across 41 different categories. This task poses a unique semantic gap challenge: the model must bridge the correspondence between a focus marker on a product reference image and a photorealistic close-up view of the indicated region, while faithfully preserving the garment's identity, without any precise prompt. To bridge this gap, we propose Cross-modal Feature Alignment Distillation (CFAD), which leverages a fine-tuned DINOv3 teacher to align both branches of a Multimodal Diffusion Transformer in a shared semantic space via dual-branch distillation. To further improve consistency between generated details and reference images, we introduce a consistency reward model that jointly scores image pairs along three quality axes and optimizes generation via reinforcement learning. Experiments show that our model DetailAnywhere significantly outperforms all state-of-the-art opensource methods across all metrics and human evaluations.

Related papers

• Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition [17.99064406157974]
  We propose a brand-new e-commerce dataset, named Fashion130k, with various occasions, models, and garment types.<n>We design a framework with Unified Multi-modal Condition (UMC) to align and integrate the text and visual prompts into generation model.<n>Experiments on real-world applications and benchmark demonstrate the effectiveness of UMC in visual consistency.
  arXiv  Detail & Related papers  (2026-05-11T07:40:03Z)
• VersaVogue: Visual Expert Orchestration and Preference Alignment for Unified Fashion Synthesis [37.779702074028044]
  VersaVogue is a unified framework for controllable fashion synthesis.<n>It supports garment generation and virtual dressing, corresponding to the design and showcase stages of the fashion lifecycle.
  arXiv  Detail & Related papers  (2026-04-08T15:31:30Z)
• Incorporating Visual Correspondence into Diffusion Model for Virtual Try-On [89.9123806553489]
  Diffusion models have shown success in virtual try-on (VTON) task.<n>The problem remains challenging to preserve the shape and every detail of the given garment due to the intrinsicity of diffusion model.<n>We propose to explicitly capitalize on visual correspondence as the prior to tame diffusion process.
  arXiv  Detail & Related papers  (2025-05-22T17:52:13Z)
• MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation [70.83668869857665]
  MMTryon is a multi-modal multi-reference VIrtual Try-ON framework. It can generate high-quality compositional try-on results by taking a text instruction and multiple garment images as inputs.
  arXiv  Detail & Related papers  (2024-05-01T11:04:22Z)
• Improving Diffusion Models for Authentic Virtual Try-on in the Wild [53.96244595495942]
  This paper considers image-based virtual try-on, which renders an image of a person wearing a curated garment. We propose a novel diffusion model that improves garment fidelity and generates authentic virtual try-on images. We present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity.
  arXiv  Detail & Related papers  (2024-03-08T08:12:18Z)
• MMFL-Net: Multi-scale and Multi-granularity Feature Learning for Cross-domain Fashion Retrieval [3.7045939497992917]
  Cross-domain fashion retrieval is a difficult task due to a wide range of consumer-to-shop (C2S) domain discrepancies. We propose a novel multi-scale and multi-granularity feature learning network (MMFL-Net), which can jointly learn global-local aggregation feature representations of clothing images. Our proposed model also combines the multi-task attribute recognition and classification module with multi-label semantic attributes and product ID labels.
  arXiv  Detail & Related papers  (2022-10-27T02:25:52Z)
• Single Stage Virtual Try-on via Deformable Attention Flows [51.70606454288168]
  Virtual try-on aims to generate a photo-realistic fitting result given an in-shop garment and a reference person image. We develop a novel Deformable Attention Flow (DAFlow) which applies the deformable attention scheme to multi-flow estimation. Our proposed method achieves state-of-the-art performance both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2022-07-19T10:01:31Z)
• Toward Accurate and Realistic Outfits Visualization with Attention to Details [10.655149697873716]
  We propose Outfit Visualization Net to capture important visual details necessary for commercial applications. OVNet consists of 1) a semantic layout generator and 2) an image generation pipeline using multiple coordinated warps. An interactive interface powered by this method has been deployed on fashion e-commerce websites and received overwhelmingly positive feedback.
  arXiv  Detail & Related papers  (2021-06-11T19:53:34Z)
• Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network [50.19558726384559]
  We propose a biologically inspired framework for image-based fashion product retrieval. Our proposed framework achieves satisfactory performance on three image-based fashion product retrieval benchmarks.
  arXiv  Detail & Related papers  (2020-10-26T06:01:09Z)
• Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification [94.77172127405846]
  We propose two key recognition patterns to better utilize the detail information of pedestrian images. CACE-Net achieves state-of-the-art performance on three public datasets.
  arXiv  Detail & Related papers  (2020-09-11T06:28:56Z)

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.