苹果发布 LiTo 技术:可从单张图片还原完整 3D 对象并保持光影一致性

Gate News 消息,3 月 17 日,苹果 AI 研究团队在 ICLR 2026 发表论文,提出 3D 生成方法 LiTo(表面光场标记化),可从单张图片生成完整 3D 对象,在切换视角时保持镜面高光、菲涅耳反射等光影效果的一致性。此前大多数 3D 重建方法只能处理几何形状或漫反射外观之一,难以还原随视角变化的光影细节。LiTo 将物体几何与视角相关外观统一编码进同一套 3D 潜在空间,再通过潜在流匹配模型在单张图片条件下生成结果。训练数据为数千个 3D 对象,每个对象从 150 个视角、3 种光照条件渲染而成,解码器通过随机抽取子样本学习完整几何与外观重建。实验显示,LiTo 在视觉质量和对输入图片的还原度上均优于现有方法 TRELLIS。论文由 Jen-Hao Rick Chang、Xiaoming Zhao(并列一作)、Dorian Chan、Oncel Tuzel 撰写,已在 arXiv 公开。

Disclaimer: The information on this page may come from third parties and does not represent the views or opinions of Gate. The content displayed on this page is for reference only and does not constitute any financial, investment, or legal advice. Gate does not guarantee the accuracy or completeness of the information and shall not be liable for any losses arising from the use of this information. Virtual asset investments carry high risks and are subject to significant price volatility. You may lose all of your invested principal. Please fully understand the relevant risks and make prudent decisions based on your own financial situation and risk tolerance. For details, please refer to Disclaimer.
Commento
0/400
Nessun commento