Patch-Based Generalized Neural Texture Upscaling

Takahiro Harada submitted a paper to arXiv on 5 November 2026 (revised 10 November 2026) proposing a lightweight neural texture upscaling method that trains a single generalized MLP on diverse texture patches and integrates it into the texture sampling stage, upscaling low-resolution textures on the fly at rendering time. Because the model is generalized rather than overfit to specific content, no per-asset training is required, and the approach cuts disk footprint by storing lower-resolution base textures, eliminates storing high-resolution textures in VRAM, and shares one set of model weights across all textures to keep GPU execution non-divergent. The authors report consistent perceptual-quality improvement over analytic upscaling methods across multiple texture classes.

Computer Science Graphics Submitted on 5 Nov 2026 v1 https://arxiv.org/abs/2611.07289v1 , last revised 10 Nov 2026 this version, v2 Title:Patch-Based Generalized Neural Texture Upscaling View PDF https://arxiv.org/pdf/2611.07289 HTML experimental https://arxiv.org/html/2611.07289v2 Abstract:We propose a lightweight neural texture upscaling method. A single generalized MLP is trained on a diverse collection of texture patches and integrated into the texture sampling stage, upscaling low-resolution textures on-the-fly at rendering time. Because the model is generalized rather than overfit to specific content, no per-asset training is required - the same model applies to any existing scene without modifying texture data or the asset pipeline. Storing lower-resolution base textures reduces disk footprint, upscaling at sampling time eliminates the need to store high-resolution textures in VRAM, and sharing a single set of model weights across all textures ensures non-divergent GPU execution. We evaluate our method across multiple texture classes, demonstrating consistent improvement over analytic upscaling methods in perceptual quality. Submission history From: Takahiro Harada view email https://arxiv.org/show-email/06a8bc53/2611.07289 Thu, 5 Nov 2026 01:11:19 UTC 9,837 KB \ v1\ https://arxiv.org/abs/2611.07289v1 v2 Tue, 10 Nov 2026 20:12:34 UTC 9,849 KB Additional Features References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .