arXiv 2511.209242026-03-24cs.CV

GaINeR：基于几何的隐式神经表示

GaINeR: Geometry-Aware Implicit Network Representation

Wrocław University of Science and Technology（沃拉夫大学科学与技术学院）；Poznań University of Technology（波兹南技术大学）；IDEAS Research Institute（IDEAS研究所）；Jagiellonian University（雅盖隆大学）

Weronika Jakubowska, Mikołaj Zieliński, Rafał Tobiasz, Krzysztof Byrski, Maciej Zięba, Dominik Belter, Przemysław Spurek

备注：: 22 pages, 16 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

GaINeR结合可训练高斯分布与神经网络，实现具有可解释几何结构的连续图像表示，支持几何一致变换、超分辨率和物理模拟集成，提升图像编辑的灵活性和物理一致性。

摘要：

隐式神经表示（INRs）广泛用于建模连续2D图像，实现高保真重建、超分辨率和压缩。SIREN、WIRE和FINER等架构展示了捕捉细图像细节的能力。然而，传统INRs缺乏显式几何结构，限制了局部编辑和物理模拟集成。为此，我们提出GaINeR（用于图像编辑的几何感知隐式神经表示），结合可训练高斯分布与基于神经网络的INR。对于给定图像坐标，模型检索K个最近的高斯分布，聚合距离加权嵌入，并通过神经网络预测RGB值。该设计实现了连续图像表示、可解释的几何结构和灵活的局部编辑，为物理感知和交互式图像编辑提供了基础。我们的方法支持几何一致的变换、无缝超分辨率和与基于物理的模拟集成。此外，高斯表示允许将单个2D图像提升为几何感知的3D表示，实现深度引导的编辑。实验表明，GaINeR在保持灵活且物理一致的图像编辑的同时实现了最先进的重建质量。我们的方法的官方实现可在https://github.com/WJakubowska/GaINeR上公开获取。

英文摘要：

Implicit Neural Representations (INRs) are widely used for modeling continuous 2D images, enabling high-fidelity reconstruction, super-resolution, and compression. Architectures such as SIREN, WIRE, and FINER demonstrate their ability to capture fine image details. However, conventional INRs lack explicit geometric structure, limiting local editing, and integration with physical simulation. To address these limitations, we propose GaINeR (Geometry-Aware Implicit Neural Representation for Image Editing), a novel framework for 2D images that combines trainable Gaussian distributions with a neural network-based INR. For a given image coordinate, the model retrieves the K nearest Gaussians, aggregates distance-weighted embeddings, and predicts the RGB value via a neural network. This design enables continuous image representation, interpretable geometric structure, and flexible local editing, providing a foundation for physically aware and interactive image manipulation. Our method supports geometry-consistent transformations, seamless super-resolution, and integration with physics-based simulations. Moreover, the Gaussian representation allows lifting a single 2D image into a geometry-aware 3D representation, enabling depth-guided editing. Experiments demonstrate that GaINeR achieves state-of-the-art reconstruction quality while maintaining flexible and physically consistent image editing. The official implementation of our method is publicly available at https://github.com/WJakubowska/GaINeR.

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。