Implicit neural representation of textures
This work addresses texture representation for real-time rendering and related applications, but it appears incremental as it builds on existing INR methods.
The paper tackles the problem of representing textures using implicit neural representations (INRs) by designing neural networks that operate continuously over UV coordinate space, resulting in good image quality with trade-offs in memory usage and rendering inference time.
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.