Implicit neural representation of textures

Albert Kwok, Zheyuan Hu, Dounia Hammou
2/2/2026
cs.CVcs.AIcs.GR

No official code found. Best implementation: PeterHUistyping/INR-Tex (4 stars, last commit 2026-02-03).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

PeterHUistyping/INR-TexCommunity64%

Implicit neural representation of textures

40Nix, TeXFeb 2, 20268 months ago
computer-graphicscomputer-visionimplicit-neural-representationmachine-learningtexture-compression+1 more

Similar Papers

Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study

83% match2026

Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural Representation

83% match2023

Dynamical Implicit Neural Representations

83% match2025

Optimizing 3D Geometry Reconstruction from Implicit Neural Representations

83% match2024

A Bag of Tricks for Efficient Implicit Neural Point Clouds

82% match2025

NTK-Guided Implicit Neural Teaching

82% match1 repo32025

Cite this paper

@article{kwok2026implicit,
  title  = {Implicit neural representation of textures},
  author = {Albert Kwok and Zheyuan Hu and Dounia Hammou},
  year   = {2026},
  eprint = {2602.02354},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2602.02354v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2602.02354.svg)](https://codeofpaper.com/paper/2602.02354)

Discussion