研究人员开发了从图像进行3D世界建模和重建的新方法。GeoState专注于创建用于预测建模的视图解耦几何状态，将场景动态与相机变化分离，并在Waymo等数据集上表现出改进的性能。WorldRecon提供了一个生成式框架，用于从无姿态的多视图图像重建大规模3D场景，生成详细的网格和PBR材质。GeoPano通过使用新颖的Pano-Attention机制来处理球形畸变并确保跨视图一致性，从而解决了从单个全景图进行几何精确3D重建的问题。 AI
影响 这些3D重建和世界建模的进步可以通过增强场景理解和生成能力来改进机器人、AR/VR和自动驾驶等应用。
排序理由 该集群包含多篇详细介绍3D重建和世界建模新方法的学术论文。
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 →
完整方法见我们的编辑标准。
arXiv:2610.22343v1 Announce Type: cross Abstract: Recent 3D world models increasingly use features from geometry foundation models (GFMs) as predictive world states, benefiting from their rich geometric priors. However, the view dependence of these features entangles scene dynami…
Reconstructing complete, high-quality meshes of large-scale scenes from unposed multi-view images requires faithful geometric grounding while plausibly completing surfaces that are unobserved or only sparsely captured. We present WorldRecon, a generative multi-view reconstruction…
arXiv:2610.21297v1 Announce Type: new Abstract: Panoramic 3D reconstruction enables the holistic recovery of complete 360 $^\circ$ scene geometry, offering significant benefits for robotics and AR/VR applications. However, directly estimating geometry from ERP images is inherentl…