arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2401.09677cs.CV
收藏

眼部运动对3D人脸重建至关重要

Eye Motion Matters for 3D Face Reconstruction

National Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School(北京大学深圳研究生院通用人工智能全国重点实验室)

Xuan Wang, Mengyuan Liu

AI总结:

针对单图像3D人脸重建忽视眼部动态的问题,提出眼部关键点调整模块与局部动态损失,可灵活再现多种眼部状态,并在两个数据集上验证了优越性能。

摘要:

单图像3D人脸重建的最新进展已在各类应用中展现出显著成效。然而,主流技术往往优先关注整体面部轮廓和表情,却忽视了眼部区域的细微动态。为此,我们提出了一个眼部关键点调整模块(Eye Landmark Adjustment Module),并辅以局部动态损失(Local Dynamic Loss),旨在捕捉眼部区域的动态特征。该模块能够灵活调整关键点,从而精确再现各种眼部状态。本文中,我们对所提方法进行了全面评估,在两个数据集上开展了大量实验。结果突显了该方法的优越性能,并表明其在应对这一特定挑战方面的重要贡献。

英文摘要:

Recent advances in single-image 3D face reconstruction have shown remarkable progress in various applications. Nevertheless, prevailing techniques tend to prioritize the global facial contour and expression, often neglecting the nuanced dynamics of the eye region. In response, we introduce an Eye Landmark Adjustment Module, complemented by a Local Dynamic Loss, designed to capture the dynamic features of the eyes area. Our module allows for flexible adjustment of landmarks, resulting in accurate recreation of various eye states. In this paper, we present a comprehensive evaluation of our approach, conducting extensive experiments on two datasets. The results underscore the superior performance of our approach, highlighting its significant contributions in addressing this particular challenge.

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。

↑