Search papers, labs, and topics across Lattice.
This paper introduces WearWow, a novel generative framework for high-resolution multi-garment virtual try-on that addresses the challenges of memory explosion and texture degradation in existing models. By employing Adaptive 2D Token Packing (ATP), WearWow efficiently manages memory usage while maintaining spatial integrity, and the Multi-dimensional Try-on Reward (MTR) system enhances texture fidelity through a dual-reward mechanism. Experimental results show that WearWow surpasses current commercial benchmarks in native 2K garment synthesis, marking a significant advancement in digital fashion technology.
WearWow sets a new standard in virtual try-on technology, achieving ultra-high-resolution synthesis while overcoming critical limitations in memory and texture quality.
Synthesizing native 2K multi-garment virtual try-on is a formidable frontier in digital fashion, critically bottlenecked by two fundamental limitations: the O(N^2) memory explosion induced by 2k conditions, and the spectral bias of diffusion models that over-smooths high-frequency fabric details. We present WearWow, an end-to-end, mask-free generative framework that pioneers ultra-high-resolution multi-garment synthesis. To mitigate the memory explosion , we propose Adaptive 2D Token Packing (ATP). ATP leverages inherent garment sparsity to algorithmically pack heterogeneous items onto a unified 2D canvas and prune uninformative background tokens, minimizing the effective sequence length and subsequent memory overhead while rigorously preserving 2D spatial priors. To rectify texture degradation, we introduce the Multi-dimensional Try-on Reward (MTR) system. MTR synergizes a Semantic Guidance Reward to explicitly drive tactile restoration with a Cloth Distribution Reward to implicitly anchor the physical distribution, a joint formulation that effectively mitigates the severe reward hacking. Furthermore, we curate WearWow-2K, an extreme-quality dataset comprising native 2K triplets, providing physically correct spatial interactions that naturally empower the model's mask-free generation. Extensive experiments demonstrate that WearWow establishes a new state-of-the-art, exceeding existing commercial baselines in native 2K multi-garment synthesis.
