GaussianBlock：通过基元和高斯构建部件感知的可组合、可编辑3D场景
GaussianBlock: Building Part-Aware Compositional and Editable 3D Scene by Primitives and Gaussians
AI总结：
提出GaussianBlock，一种部件感知的组合式3D重建方法，通过基元与3D高斯的混合表示及注意力引导中心化损失，实现语义解纠缠、可编辑且高保真的场景重建。
摘要：
近年来，随着神经辐射场和高斯泼溅技术的发展，3D重建技术已实现极高的保真度。然而，这些方法学习到的潜在表示高度纠缠且缺乏可解释性。本文提出一种新颖的部件感知组合式重建方法，称为GaussianBlock，它能够实现语义一致且解纠缠的表示，允许类似积木的精确且物理性的编辑，同时保持高保真度。我们的GaussianBlock引入了一种混合表示，结合了基元（以其灵活的可操作性和可编辑性著称）和3D高斯（在重建质量上表现出色）两者的优势。具体而言，我们通过一种新颖的、源自2D语义先验的注意力引导中心化损失，辅以动态分裂与融合策略，实现了语义一致的基元。此外，我们利用与基元混合的3D高斯来细化结构细节并增强保真度。同时，采用绑定继承策略来加强并维持两者之间的联系。我们的重建场景在多个基准上被证明是解纠缠的、组合式的且紧凑的，能够实现无缝、直接且精确的编辑，同时保持高质量。
英文摘要：
Recently, with the development of Neural Radiance Fields and Gaussian Splatting, 3D reconstruction techniques have achieved remarkably high fidelity. However, the latent representations learnt by these methods are highly entangled and lack interpretability. In this paper, we propose a novel part-aware compositional reconstruction method, called GaussianBlock, that enables semantically coherent and disentangled representations, allowing for precise and physical editing akin to building blocks, while simultaneously maintaining high fidelity. Our GaussianBlock introduces a hybrid representation that leverages the advantages of both primitives, known for their flexible actionability and editability, and 3D Gaussians, which excel in reconstruction quality. Specifically, we achieve semantically coherent primitives through a novel attention-guided centering loss derived from 2D semantic priors, complemented by a dynamic splitting and fusion strategy. Furthermore, we utilize 3D Gaussians that hybridize with primitives to refine structural details and enhance fidelity. Additionally, a binding inheritance strategy is employed to strengthen and maintain the connection between the two. Our reconstructed scenes are evidenced to be disentangled, compositional, and compact across diverse benchmarks, enabling seamless, direct and precise editing while maintaining high quality.
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。
