GSD：用于3D重建的视图引导高斯泼溅扩散模型
GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction
AI总结：
本研究提出GSD方法，基于高斯泼溅表示和扩散模型实现单视图3D重建，通过视图引导采样、2D扩散增强渲染质量，在CO3D数据集上展现出更优的重建效果。
摘要：
我们提出了GSD，这是一种基于高斯泼溅（Gaussian Splatting, GS）表示的扩散模型方法，用于从单视图进行3D物体重建。现有方法因表示方式不当，存在3D几何结构不一致或渲染质量一般的问题。我们通过采用当前最先进的3D显式表示——高斯泼溅，以及一个无条件扩散模型，着手解决这些缺陷。该模型学习生成由多组GS椭球表示的3D物体。凭借这些强大的生成式3D先验，尽管是无监督学习，该扩散模型无需进一步微调即可用于视图引导的重建。这一过程通过高效且灵活的泼溅函数传播细粒度2D特征，并结合引导去噪采样流程实现。此外，我们还采用了一个2D扩散模型来提升渲染保真度，并通过打磨和复用渲染图像来提高重建的GS质量。最终重建的物体具备显式的高质量3D结构和纹理，可在任意视图下高效渲染。在具有挑战性的真实世界CO3D数据集上的实验证明了我们方法的优越性。项目页面：https://yxmu.foo/GSD/
英文摘要：
We present GSD, a diffusion model approach based on Gaussian Splatting (GS) representation for 3D object reconstruction from a single view. Prior works suffer from inconsistent 3D geometry or mediocre rendering quality due to improper representations. We take a step towards resolving these shortcomings by utilizing the recent state-of-the-art 3D explicit representation, Gaussian Splatting, and an unconditional diffusion model. This model learns to generate 3D objects represented by sets of GS ellipsoids. With these strong generative 3D priors, though learning unconditionally, the diffusion model is ready for view-guided reconstruction without further model fine-tuning. This is achieved by propagating fine-grained 2D features through the efficient yet flexible splatting function and the guided denoising sampling process. In addition, a 2D diffusion model is further employed to enhance rendering fidelity, and improve reconstructed GS quality by polishing and re-using the rendered images. The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views. Experiments on the challenging real-world CO3D dataset demonstrate the superiority of our approach. Project page: https://yxmu.foo/GSD/
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。
