Gen3DSR：通过分而治之从单视图进行可泛化的3D场景重建
Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View
AI总结：
提出基于分而治之策略的混合模块化方法Gen3DSR，通过整体提取深度和语义信息并结合物体级重建，实现无需重训即可泛化到多种场景的单视图3D重建。
摘要：
单视图3D重建目前主要从两个主导视角进行：使用3D数据监督重建多样性有限的场景，或使用大型图像先验重建多样的单一物体。然而，现实场景远比这复杂，超出了这些方法的能力。因此，我们提出了一种遵循分而治之策略的混合方法。我们首先整体处理场景，提取深度和语义信息，然后利用物体级方法对各个组件进行详细重建。通过将问题分解为更简单的任务，我们的系统能够泛化到各种类型的场景，而无需重新训练或微调。我们特意将流水线设计为高度模块化，具有独立、自包含的模块，以避免对整个系统进行端到端训练。这使得该流水线能够自然改进，因为未来的方法可以替换各个模块。我们在合成和真实场景上展示了我们方法的重建性能，与先前工作相比表现更优。项目页面：https://andreeadogaru.github.io/Gen3DSR
英文摘要：
Single-view 3D reconstruction is currently approached from two dominant perspectives: reconstruction of scenes with limited diversity using 3D data supervision or reconstruction of diverse singular objects using large image priors. However, real-world scenarios are far more complex and exceed the capabilities of these methods. We therefore propose a hybrid method following a divide-and-conquer strategy. We first process the scene holistically, extracting depth and semantic information, and then leverage an object-level method for the detailed reconstruction of individual components. By splitting the problem into simpler tasks, our system is able to generalize to various types of scenes without retraining or fine-tuning. We purposely design our pipeline to be highly modular with independent, self-contained modules, to avoid the need for end-to-end training of the whole system. This enables the pipeline to naturally improve as future methods can replace the individual modules. We demonstrate the reconstruction performance of our approach on both synthetic and real-world scenes, comparing favorable against prior works. Project page: https://andreeadogaru.github.io/Gen3DSR
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。
