← Back to all news
arXiv Computer Vision By Xujie Zhang, Ente Lin, Michael Kampffmeyer, Zhenyu Xie, Jiang Li, Ting Liu, Xiaochao Qu, Luoqi Liu, Xiaodan Liang

MMTryon: Multi-Modal Multi-Reference Control for High-Quality Fashion Generation

Read the original on arXiv Computer Vision →

MMTryon is a multi‑modal, multi‑reference virtual try‑on framework that generates high‑quality compositional try‑on results using text instructions and multiple garment images. It addresses three overlooked problems: supporting multiple try‑on items, allowing dressing style specification via text, and eliminating reliance on segmentation models by using a parsing‑free garment encoder and a scalable data generation pipeline. Experiments on high‑resolution benchmarks and in‑the‑wild test sets show MMTryon outperforms state‑of‑the‑art methods qualitatively and quantitatively.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 21

TAMF-VTON: Token-Wise Sparse Adaptation for Mask-Free Virtual Try-On

TAMF-VTON is a diffusion-based virtual try‑on system that eliminates the need for segmentation masks, parsing maps, pose representations, or spatial controls during inference. It uses token‑wise sparse Mixture‑of‑Experts adaptation to provide input‑dependent capacity, along with timestep‑weighted frequency supervision and adaptive offline data construction to improve high‑frequency reconstruction and cross‑category training. The method achieves top performance on single‑garment VITON‑HD and DressCode benchmarks, supports multi‑garment transfer, and can generate 1K‑resolution images in under 15 seconds on an RTX 4090.

By Jie Wang, Qian He, Gaofeng He, Xiaogang Jin, Huamin Wang
diffusioncomputer-visionbenchmarks
More like this →