神经纹理散射：用于视图合成、几何和动态重建的表达性3D高斯散射
Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
AI总结：
本文提出神经纹理散射方法，通过全局神经场提升3D高斯散射在视图合成、几何和动态重建中的性能。
摘要：
3D高斯散射（3DGS）已发展为高质量新视图合成的领先方法，众多变体将其应用扩展到广泛的情景重建任务中。尽管其成功，3DGS的表示能力仍受限于使用3D高斯核来建模局部变化。近期的工作提出了通过增加每个原始体的容量来增强3DGS，例如每个散射点的纹理，以提高其表达性。然而，这些每个散射点纹理方法主要针对密集的新视图合成，使用较少的高斯原始体，当应用于更一般的重建场景时，其效果往往会减弱。在本文中，我们旨在在广泛的重建任务中，包括新视图合成、几何和动态重建，无论输入是稀疏还是密集，都实现对最新3DGS变体的实质性性能提升。为此，我们引入了神经纹理散射（NTS）。我们方法的核心是一个全局神经场（表示为三平面和神经解码器的混合），它为每个原始体预测局部外观和几何场。通过利用这一共享的全局表示，该表示在原始体之间建模局部纹理场，我们显著减少了模型大小，并促进了高效的全局信息交换，展示了在不同任务上的强大泛化能力。此外，我们对局部纹理场的神经建模引入了视图和时间相关的表达性影响，这是现有方法未能考虑的关键因素。广泛的实验表明，神经纹理散射在多个基准上一致地提高了模型性能，并实现了最先进的结果。
英文摘要：
3D Gaussian Splatting (3DGS) has emerged as a leading approach for high-quality novel view synthesis, with numerous variants extending its applicability to a broad spectrum of 3D and 4D scene reconstruction tasks. Despite its success, the representational capacity of 3DGS remains limited by the use of 3D Gaussian kernels to model local variations. Recent works have proposed to augment 3DGS with additional per-primitive capacity, such as per-splat textures, to enhance its expressiveness. However, these per-splat texture approaches primarily target dense novel view synthesis with a reduced number of Gaussian primitives, and their effectiveness tends to diminish when applied to more general reconstruction scenarios. In this paper, we aim to achieve concrete performance improvement over state-of-the-art 3DGS variants across a wide range of reconstruction tasks, including novel view synthesis, geometry and dynamic reconstruction, under both sparse and dense input settings. To this end, we introduce Neural Texture Splatting (NTS). At the core of our approach is a global neural field (represented as a hybrid of a tri-plane and a neural decoder) that predicts local appearance and geometric fields for each primitive. By leveraging this shared global representation that models local texture fields across primitives, we significantly reduce model size and facilitate efficient global information exchange, demonstrating strong generalization across tasks. Furthermore, our neural modeling of local texture fields introduces expressive view- and time-dependent effects, a critical aspect that existing methods fail to account for. Extensive experiments show that Neural Texture Splatting consistently improves models and achieves state-of-the-art results across multiple benchmarks.
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。
