paper-with-me

홈 › Papers

UniFit: Towards Universal Virtual Try-on with MLLM-Guided Semantic Alignment

2025-11-19 · Wei Zhang, Yeying Jin, Xin Li, Yan Zhang, Xiaofeng Cong, Cong Wang, Fengcai Qiao, zhichao Lian arxiv

Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework that can flexibly handle diverse and complex tasks remains a major challenge. Recent methods explore multi-task VTON frameworks guided by textual instructions, yet they still face two key limitations: (1) semantic gap between text instructions and reference images, and (2) data scarcity in complex scenarios. To address these challenges, we propose UniFit, a universal VTON framework driven by a Multimodal Large Language Model (MLLM). Specifically, we introduce an MLLM-Guided Semantic Alignment Module (MGSA), which integrates multimodal inputs using an MLLM and a set of learnable queries. By imposing a semantic alignment loss, MGSA captures cross-modal semantic relationships and provides coherent and explicit semantic guidance for the generative process, thereby reducing the semantic gap. Moreover, by devising a two-stage progressive training strategy with a self-synthesis pipeline, UniFit is able to learn complex tasks from limited data. Extensive experiments show that UniFit not only supports a wide range of VTON tasks, including multi-garment and model-to-model try-on, but also achieves state-of-the-art performance. The source code and pretrained models are available at https://github.com/zwplus/UniFit.

📄 PDF Abstract BibTeX arXiv:2511.15831

Code (0)

등록된 구현이 없습니다.

Tasks

Virtual Try-on

Similar Papers 제목 키워드 기반

Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation

2025-11-25 · Changyue Li, Jiaying Li, Youliang Yuan, Jiaming He 외 arxiv

Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-Aware Hijacking. We explore the feasibili…

Autonomous Driving

Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization

2026-01-30 · Hui Lu, Yi Yu, Yiming Yang, Chenyu Yi 외 arxiv

Targeted adversarial attacks on closed-source multimodal large language models (MLLMs) have been increasingly explored under black-box transfer, yet prior methods are predominantly sample-specific and offer limited reusa…

MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation

2026-05-11 · Ziyi Wang, Xianping Ma, Ziyao Wang, Hongyang Zhang 외 arxiv

The multimodal fusion of images and scene captions has been extensively explored and applied in various fields. However, when dealing with complex remote sensing (RS) scenes, existing studies have predominantly concentra…

Semantic SegmentationScene Segmentation

UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning

2025-10-15 · Tiancheng Gu, Kaicheng Yang, Kaichen Zhang, Xiang An 외 arxiv

Universal multimodal embedding models are foundational to various tasks. Existing approaches typically employ in-batch negative mining by measuring the similarity of query-candidate pairs. However, these methods often st…

Representation Learning

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

2026-02-05 · Qi Li, Yanzhe Zhao, Yongxin Zhou, Yameng Wang 외 arxiv

Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various modalities for a given query. However, their practical application is of…