MetricGrids:使用基于初等度量网格的隐式神经表示进行任意非线性逼近
MetricGrids: Arbitrary Nonlinear Approximation with Elementary Metric Grids based Implicit Neural Representation
AI总结:
本文提出 MetricGrids,通过构建多个遵循泰勒展开原理的初等度量网格作为高阶项来逼近复杂非线性信号,并结合稀疏感知哈希编码与高阶外推解码器,在2D和3D重建中取得更优精度。
摘要:
本文提出了 MetricGrids,这是一种新颖的基于网格的神经表示,它结合了不同度量空间中的初等度量网格,以逼近复杂的非线性信号。尽管基于网格的表示因其效率和可扩展性而被广泛采用,但现有的对连续空间点进行线性索引的特征网格只能提供退化的线性潜在空间表示,而且后续的紧凑解码器无法充分弥补这种表示在表达复杂非线性信号方面的不足。为了解决这一问题,同时保留规则网格结构的简洁性,我们的方法建立在标准的基于网格范式之上,遵循泰勒展开原理,构建多个初等度量网格作为高阶项,以逼近复杂的非线性。此外,我们利用基于网格不同稀疏度的哈希编码来增强模型的紧凑性,以避免有害的哈希冲突;并使用高阶外推解码器来减少显式网格存储需求。在二维和三维重建上的实验结果表明,所提方法在多种信号类型上均具有卓越的拟合和渲染精度,验证了其鲁棒性和泛化能力。代码可在 https://github.com/wangshu31/MetricGrids 获取。
英文摘要:
This paper presents MetricGrids, a novel grid-based neural representation that combines elementary metric grids in various metric spaces to approximate complex nonlinear signals. While grid-based representations are widely adopted for their efficiency and scalability, the existing feature grids with linear indexing for continuous-space points can only provide degenerate linear latent space representations, and such representations cannot be adequately compensated to represent complex nonlinear signals by the following compact decoder. To address this problem while keeping the simplicity of a regular grid structure, our approach builds upon the standard grid-based paradigm by constructing multiple elementary metric grids as high-order terms to approximate complex nonlinearities, following the Taylor expansion principle. Furthermore, we enhance model compactness with hash encoding based on different sparsities of the grids to prevent detrimental hash collisions, and a high-order extrapolation decoder to reduce explicit grid storage requirements. experimental results on both 2D and 3D reconstructions demonstrate the superior fitting and rendering accuracy of the proposed method across diverse signal types, validating its robustness and generalizability. Code is available at https://github.com/wangshu31/MetricGrids}{https://github.com/wangshu31/MetricGrids.
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。