纹理的隐式神经表示

摘要

隐式神经表示（INR）已在多个领域被证明具有高精度与高效性。本研究探索了如何将不同神经网络设计为新型纹理INR，该表示在输入UV坐标空间上以连续方式而非离散方式运行。通过系统实验，我们证明这些INR在图像质量方面表现优异，同时具备理想的内存使用效率和渲染推理速度。本文深入分析了这些性能指标间的平衡关系，并进一步探究了实时渲染及相关下游任务中的多种应用场景，例如Mipmap拟合与INR空间生成。

English

Implicit neural representation (INR) has proven to be accurate and efficient in various domains. In this work, we explore how different neural networks can be designed as a new texture INR, which operates in a continuous manner rather than a discrete one over the input UV coordinate space. Through thorough experiments, we demonstrate that these INRs perform well in terms of image quality, with considerable memory usage and rendering inference time. We analyze the balance between these objectives. In addition, we investigate various related applications in real-time rendering and down-stream tasks, e.g. mipmap fitting and INR-space generation.

纹理的隐式神经表示

Implicit neural representation of textures

摘要

Support