arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.18643cs.CVcs.AIeess.IV
收藏

面向增强现实的鞋履三维重建

3D Reconstruction of Shoes for Augmented Reality

Department of Electronics and Computer Engineering(电子与计算机工程系)

Pratik Shrestha, Sujan Kapali, Swikar Gautam, Vishal Pokharel, Santosh Giri

AI总结:

本文提出基于 3D Gaussian Splatting 的移动端鞋履三维重建与 AR 交互框架,并构建 3120 张图像的分割数据集,实现高保真虚拟试穿。

摘要:

本文介绍了一种基于移动端的解决方案,通过三维建模和增强现实(AR)改善在线购鞋体验,并利用 3D Gaussian Splatting 的高效性。针对静态二维图像的局限性,该框架可由二维图像生成逼真的三维鞋履模型,平均峰值信噪比(PSNR)达到 32,并通过智能手机实现沉浸式 AR 交互。研究创建了一个包含 3120 张图像的定制鞋履分割数据集,其中表现最佳的分割模型取得了 0.95 的交并比(IoU)分数。本文展示了三维建模和 AR 通过提供逼真虚拟交互来革新在线购物的潜力,并可应用于更广泛的时尚品类。

英文摘要:

This paper introduces a mobile-based solution that enhances online shoe shopping through 3D modeling and Augmented Reality (AR), leveraging the efficiency of 3D Gaussian Splatting. Addressing the limitations of static 2D images, the framework generates realistic 3D shoe models from 2D images, achieving an average Peak Signal-to-Noise Ratio (PSNR) of 32, and enables immersive AR interactions via smartphones. A custom shoe segmentation dataset of 3120 images was created, with the best-performing segmentation model achieving an Intersection over Union (IoU) score of 0.95. This paper demonstrates the potential of 3D modeling and AR to revolutionize online shopping by offering realistic virtual interactions, with applicability across broader fashion categories.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑