Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off

• URL: http://arxiv.org/abs/2603.22607v1
• Date: Mon, 23 Mar 2026 22:12:40 GMT
• Title: Dress-ED: Instruction-Guided Editing for Virtual Try-On and Try-Off
• Abstract summary: We introduce the Dress Editing dataset (Dress-ED), the first large-scale benchmark that unifies VTON, VTOFF, and text-guided garment editing.<n>Dress-ED comprises over 146k verified quadruplets spanning three garment categories and seven edit types.
• Score: 91.61470961531889
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in Virtual Try-On (VTON) and Virtual Try-Off (VTOFF) have greatly improved photo-realistic fashion synthesis and garment reconstruction. However, existing datasets remain static, lacking instruction-driven editing for controllable and interactive fashion generation. In this work, we introduce the Dress Editing Dataset (Dress-ED), the first large-scale benchmark that unifies VTON, VTOFF, and text-guided garment editing within a single framework. Each sample in Dress-ED includes an in-shop garment image, the corresponding person image wearing the garment, their edited counterparts, and a natural-language instruction of the desired modification. Built through a fully automated multimodal pipeline that integrates MLLM-based garment understanding, diffusion-based editing, and LLM-guided verification, Dress-ED comprises over 146k verified quadruplets spanning three garment categories and seven edit types, including both appearance (e.g., color, pattern, material) and structural (e.g., sleeve length, neckline) modifications. Based on this benchmark, we further propose a unified multimodal diffusion framework that jointly reasons over linguistic instructions and visual garment cues, serving as a strong baseline for instruction-driven VTON and VTOFF. Dataset and code will be made publicly available.

Related papers

• Garments2Look: A Multi-Reference Dataset for High-Fidelity Outfit-Level Virtual Try-On with Clothing and Accessories [27.58214524973654]
  Garments2Look is the first large-scale multimodal dataset for outfit-level VTON.<n>It comprises 80K many-garments-to-one-look pairs across 40 major categories and 300+ fine-grained subcategories.<n>To balance authenticity and diversity, we propose a synthesis pipeline.
  arXiv  Detail & Related papers  (2026-03-14T23:30:32Z)
• MuGa-VTON: Multi-Garment Virtual Try-On via Diffusion Transformers with Prompt Customization [19.780800887427937]
  We introduce MuGa-VTON, a unified multi-garment diffusion framework that jointly models upper and lower garments together with person identity in a shared latent space.<n>This architecture supports prompt-based customization, allowing fine-grained garment modifications with minimal user input.
  arXiv  Detail & Related papers  (2025-08-11T21:45:07Z)
• EditGarment: An Instruction-Based Garment Editing Dataset Constructed with Automated MLLM Synthesis and Semantic-Aware Evaluation [6.00676826743099]
  We present an automated dataset pipeline for constructing a garment editing.<n>We first define six editing instruction categories aligned with real-world fashion to guide the generation of balanced instruction-image triplets.<n>Second, we introduce Fashion Edit Score, a semantic-aware evaluation metric that captures semantic dependencies between garment attributes and provides reliable supervision during construction.
  arXiv  Detail & Related papers  (2025-08-05T14:28:45Z)
• Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals [76.96387718150542]
  We present Text-Enhanced MUlti-category Virtual Try-Off (TEMU-VTOFF)<n>Our architecture is designed to receive garment information from multiple modalities like images, text, and masks to work in a multi-category setting.<n> Experiments on VITON-HD and Dress Code datasets show that TEMU-VTOFF sets a new state-of-the-art on the VTOFF task.
  arXiv  Detail & Related papers  (2025-05-27T11:47:51Z)
• AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea [88.79769371584491]
  We present AnyEdit, a comprehensive multi-modal instruction editing dataset.<n>We ensure the diversity and quality of the AnyEdit collection through three aspects: initial data diversity, adaptive editing process, and automated selection of editing results.<n>Experiments on three benchmark datasets show that AnyEdit consistently boosts the performance of diffusion-based editing models.
  arXiv  Detail & Related papers  (2024-11-24T07:02:56Z)
• EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing [114.14164860467227]
  We propose EditRoom, a framework capable of executing a variety of layout edits through natural language commands.<n>Specifically, EditRoom leverages Large Language Models (LLMs) for command planning and generates target scenes.<n>We have developed an automatic pipeline to augment existing 3D scene datasets and introduced EditRoom-DB, a large-scale dataset with 83k editing pairs.
  arXiv  Detail & Related papers  (2024-10-03T17:42:24Z)
• IMAGDressing-v1: Customizable Virtual Dressing [58.44155202253754]
  IMAGDressing-v1 is a virtual dressing task that generates freely editable human images with fixed garments and optional conditions. IMAGDressing-v1 incorporates a garment UNet that captures semantic features from CLIP and texture features from VAE. We present a hybrid attention module, including a frozen self-attention and a trainable cross-attention, to integrate garment features from the garment UNet into a frozen denoising UNet.
  arXiv  Detail & Related papers  (2024-07-17T16:26:30Z)
• Fashion Matrix: Editing Photos by Just Talking [66.83502497764698]
  We develop a hierarchical AI system called Fashion Matrix dedicated to editing photos by just talking. Fashion Matrix employs Large Language Models (LLMs) as its foundational support and engages in iterative interactions with users. Visual Foundation Models are leveraged to generate edited images from text prompts and masks, thereby facilitating the automation of fashion editing processes.
  arXiv  Detail & Related papers  (2023-07-25T04:06:25Z)

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.