← Back to all news
arXiv AI

Training-Free, Identity-Preserving Image Editing for Fashion Pose Alignment and Normalization

arXiv:2501. 13692v2 Announce Type: replace-cross Abstract: Diffusion models have recently unlocked new possibilities in editing images of real-world objects.

Related stories

arXiv Computer Vision
Sep 3

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

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.

By Xujie Zhang, Ente Lin, Michael Kampffmeyer, Zhenyu Xie, Jiang Li, Ting Liu, Xiaochao Qu, Luoqi Liu, Xiaodan Liang
computer-visionmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 3

FitControler: Toward Fit-Aware Virtual Try-On

FitControler introduces a fit-aware virtual try‑on system that adds garment fit control to existing VTON models. It uses a fit‑aware layout generator and a multi‑scale fit injector to redraw body‑garment layouts and render garments that match those layouts. The authors also release a new Fit4Men dataset of 13,000 body‑garment pairs and two fit consistency metrics to evaluate fit quality.

By Lu Yang, Yicheng Liu, Letian Zhou, Yanan Li, Xiang Bai, Hao Lu
More like this →
arXiv Computer Vision
Sep 7

HyperBones: Realtime Bone-driven Neural Garment Simulation with Hypernetwork Conditioning

The paper introduces HyperBones, a real‑time garment simulation framework that combines a reduced‑space neural dynamics simulator with a lightweight neural network correcting Linear Blend Skinning (LBS) at a coarse level, and a convolutional MLP for fine‑scale wrinkle recovery in UV space. By decoupling identity‑specific computation from shape conditioning through a hypernetwork, the method achieves high performance without an offline simulator, delivering physically plausible dynamics across diverse motions and unseen body shapes. Experiments demonstrate a speedup of over 30× compared to state‑of‑the‑art autoregressive neural simulators, reaching interactive inference at roughly 1 ms per frame on a consumer GPU.

By Astitva Srivastava, Hsiao-Yu Chen, Ryan Goldade, Philipp Herholz, Zhongshi Jiang, Gene Wei-Chin Lin, Lingchen Yang, Nikolaos Sarafianos, Tuur Stuyck, Avinash Sharma, Egor Larionov
benchmarks
More like this →