研究人员开发了一种新颖的方法，仅使用标准的低速相机来捕获和重建高速动态3D场景。该技术通过用快速、顺序的颜色编码光序列照亮场景来编码时间信息，从而实现同步多视图捕获。然后，使用动态高斯泼溅方法来解码此编码信息并创建场景的体积表示。此方法绕过了对专用高速相机或修改光学器件的需求，为实现高速体积场景重建提供了一种更易于访问的方式。 AI
影响 无需专用硬件即可实现高速3D场景捕获，可能对机器人和虚拟现实等领域产生影响。
排序理由 描述一种用于高速体积场景重建的新颖方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2604.26920v1 Announce Type: new Abstract: The task of capturing and rendering 3D dynamic scenes from 2D images has become increasingly popular in recent years. However, most conventional cameras are bandwidth-limited to 30-60 FPS, restricting these methods to static or slow…
arXiv:2503.17897v2 Announce Type: replace-cross Abstract: We present a real-time global illumination approach along with a pipeline for dynamic 3D Gaussian models and meshes. Building on a formulated surface light transport model for 3D Gaussians, we address key performance chall…
The task of capturing and rendering 3D dynamic scenes from 2D images has become increasingly popular in recent years. However, most conventional cameras are bandwidth-limited to 30-60 FPS, restricting these methods to static or slowly evolving scenes. While overcoming bandwidth l…