研究人员开发了 ManiSplat，一个从单目视频重建动态3D场景的新框架。该方法将机器人、物体和背景解耦为独立的高斯泼溅子场，从而实现可控的数字孪生。ManiSplat 使用面向任务的对齐模块来确保时间连贯性和物理一致性，使重建的场景适用于机器人任务和策略学习。 AI
影响 为训练机器人策略提供更逼真的模拟环境。
排序理由 该集群包含一篇详细介绍3D场景重建新方法的论文。
在 Hugging Face Daily Papers 阅读 →
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
Reconstructing dynamic and interactive 3D scenes from real-world observations remains a fundamental challenge in computer vision and robotics. While recent advances in 3D Gaussian Splatting have enabled high-fidelity static reconstruction, extending it to interactive environments…
arXiv:2606.10645v1 Announce Type: new Abstract: Reconstructing dynamic and interactive 3D scenes from real-world observations remains a fundamental challenge in computer vision and robotics. While recent advances in 3D Gaussian Splatting have enabled high-fidelity static reconstr…
Reconstructing dynamic and interactive 3D scenes from real-world observations remains a fundamental challenge in computer vision and robotics. While recent advances in 3D Gaussian Splatting have enabled high-fidelity static reconstruction, extending it to interactive environments…