可泛化稀疏视角3D重建从无约束图像
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
AI总结：
本文提出GenWildSplat框架，通过学习几何先验在无场景优化情况下实现稀疏视角户外3D重建，利用外观适配器和语义分割处理光照和遮挡，实现跨不同光照和遮挡模式的泛化。
摘要：
从稀疏、未对准的图像重建3D场景在真实条件下仍具有挑战性，因为存在变化的光照和瞬时遮挡。现有方法依赖于场景特定的优化使用外观嵌入或动态掩码，这需要大量的场景特定训练并在稀疏视角下失效。此外，对有限场景的评估提出了泛化问题。我们提出了GenWildSplat，一个用于稀疏视角户外重建的前馈框架，无需场景特定优化。给定未对准的互联网图像，GenWildSplat在标准空间中使用学习的几何先验预测深度、相机参数和3D高斯。外观适配器调节目标光照条件下的外观，而语义分割处理瞬时物体。通过在合成和真实数据上的课程学习，GenWildSplat在多样化的光照和遮挡模式下实现泛化。在PhotoTourism和MegaScenes基准上的评估显示，GenWildSplat实现了最先进的前馈渲染质量，实现无测试时间优化的实时推理。
英文摘要：
Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on scene-specific optimization using appearance embeddings or dynamic masks, which requires extensive per-scene training and fails under sparse views. Moreover, evaluations on limited scenes raise questions about generalization. We present GenWildSplat, a feed-forward framework for sparse-view outdoor reconstruction that requires no per-scene optimization. Given unposed internet images, GenWildSplat predicts depth, camera parameters, and 3D Gaussians in a canonical space using learned geometric priors. An appearance adapter modulates appearance for target lighting conditions, while semantic segmentation handles transient objects. Through curriculum learning on synthetic and real data, GenWildSplat generalizes across diverse illumination and occlusion patterns. Evaluations on PhotoTourism and MegaScenes benchmark demonstrate state-of-the-art feed-forward rendering quality, achieving real-time inference without test-time optimization
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
