Scholarlink

<p>Facial geometry and appearance capture have demonstrated tremendous success in 3D scanning real humans in studios. Recent works propose democratizing this technique while keeping the results close to the studio. However, they are still inconvenient for daily usage. In addition, they focus on an easier problem of only capturing facial skin. This paper proposes a novel method for high-quality face capture, featuring an easy-to-use system and the ability to model the complete face with skin, mouth interior, hair, and eyes. We reconstruct facial geometry and appearance from a single co-located smartphone flashlight sequence captured in a dim room where the smartphone flashlight is the dominant light source (<i>e.g.</i> rooms with curtains or capture data at night). To model the complete face, we propose a novel hybrid representation to effectively model both eyes and other facial regions and novel techniques to learn it from images. We apply a combined lighting model to represent real illuminations compactly and exploit a morphable face albedo model as the reflectance priors to disentangle diffuse and specular. Experiments show that our method can capture high-quality 3D relightable scans. Our code is released at <a href="https://github.com/yxuhan/CoRA.">https://github.com/yxuhan/CoRA.</a></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

High-Quality Facial Geometry and Appearance Capture at Home

  • 期刊论文

  • 发表日期：

    2026年5月5日

查看全文
  • Feng Xu,
  • Yuxuan Han,
  • Junfeng Lyu

摘要

Facial geometry and appearance capture have demonstrated tremendous success in 3D scanning real humans in studios. Recent works propose democratizing this technique while keeping the results close to the studio. However, they are still inconvenient for daily usage. In addition, they focus on an easier problem of only capturing facial skin. This paper proposes a novel method for high-quality face capture, featuring an easy-to-use system and the ability to model the complete face with skin, mouth interior, hair, and eyes. We reconstruct facial geometry and appearance from a single co-located smartphone flashlight sequence captured in a dim room where the smartphone flashlight is the dominant light source (e.g. rooms with curtains or capture data at night). To model the complete face, we propose a novel hybrid representation to effectively model both eyes and other facial regions and novel techniques to learn it from images. We apply a combined lighting model to represent real illuminations compactly and exploit a morphable face albedo model as the reflectance priors to disentangle diffuse and specular. Experiments show that our method can capture high-quality 3D relightable scans. Our code is released at https://github.com/yxuhan/CoRA.