Virtual Try-on (VTON) involves generating images of a person wearing selected
garments. Diffusion-based methods, in particular, can create high-quality
images, but they struggle to maintain the identities of the input garments. We
identified this problem stems from the specifics in the training formulation
for diffusion. To address this, we propose a unique training scheme that limits
the scope in which diffusion is trained. We use a control image that perfectly
aligns with the target image during training. In turn, this accurately
preserves garment details during inference. We demonstrate our method not only
effectively conserves garment details but also allows for layering, styling,
and shoe try-on. Our method runs multi-garment try-on in a single inference
cycle and can support high-quality zoomed-in generations without training in
higher resolutions. Finally, we show our method surpasses prior methods in
accuracy and quality.

提出了一种独特的训练方案来解决扩散的训练公式中维持输入服装身份的问题，并且通过多衣物试穿单次推断循环实现高质量的放大生成。

ACDG-VTON：精准和受限扩散生成虚拟试穿

ACDG-VTON: Accurate and Contained Diffusion Generation for Virtual  Try-On

Image-based virtual try-on (VTON), which aims to generate an outfitted image
of a target human wearing an in-shop garment, is a challenging image-synthesis
task calling for not only high fidelity of the outfitted human but also full
preservation of garment details. To tackle this issue, we propose Outfitting
over Try-on Diffusion (OOTDiffusion), leveraging the power of pretrained latent
diffusion models and designing a novel network architecture for realistic and
controllable virtual try-on. Without an explicit warping process, we propose an
outfitting UNet to learn the garment detail features, and merge them with the
target human body via our proposed outfitting fusion in the denoising process
of diffusion models. In order to further enhance the controllability of our
outfitting UNet, we introduce outfitting dropout to the training process, which
enables us to adjust the strength of garment features through classifier-free
guidance. Our comprehensive experiments on the VITON-HD and Dress Code datasets
demonstrate that OOTDiffusion efficiently generates high-quality outfitted
images for arbitrary human and garment images, which outperforms other VTON
methods in both fidelity and controllability, indicating an impressive
breakthrough in virtual try-on. Our source code is available at
this https URL

使用 Outfitting over Try-on Diffusion（OOTDiffusion）方法，结合预训练的潜在扩散模型和创新的网络架构，可以有效地生成高质量、逼真且可控的虚拟试穿图像，突破了现有虚拟试穿方法在逼真度和可控性方面的局限。

OOTDiffusion：基于融合的潜在扩散技术的控制性虚拟试穿

OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable  Virtual Try-on

To make 3D human avatars widely available, we must be able to generate a
variety of 3D virtual humans with varied identities and shapes in arbitrary
poses. This task is challenging due to the diversity of clothed body shapes,
their complex articulations, and the resulting rich, yet stochastic geometric
detail in clothing. Hence, current methods to represent 3D people do not
provide a full generative model of people in clothing. In this paper, we
propose a novel method that learns to generate detailed 3D shapes of people in
a variety of garments with corresponding skinning weights. Specifically, we
devise a multi-subject forward skinning module that is learned from only a few
posed, un-rigged scans per subject. To capture the stochastic nature of
high-frequency details in garments, we leverage an adversarial loss formulation
that encourages the model to capture the underlying statistics. We provide
empirical evidence that this leads to realistic generation of local details
such as wrinkles. We show that our model is able to generate natural human
avatars wearing diverse and detailed clothing. Furthermore, we show that our
method can be used on the task of fitting human models to raw scans,
outperforming the previous state-of-the-art.

这篇论文提出了一种新方法，使用前向蒙皮模块和对抗网络模型，仅从少量生动的数据中学习生成多样化的 3D 人形模型，以便能够更自然地生成身着不同服装的人形模型，并且还可用于将人形模型拟合到原始扫描数据上。