Skip to main content
GameDev.net gamedev.net

Materials

24 items across game development

24 results

News

DealMaTe: Multi-Dimensional Material Transfer via Diffusion Transformer

DealMaTe proposes a diffusion-transformer approach for multi-dimensional material transfer, aiming to move more than just color or texture between assets. Published in ACM Transactions on Graphics,...

Nisha HuangYizhou LinJie GuoXiu LiTong-Yee LeeZitong Yu ·
graphics research materials diffusion model lookdev technical art
News

Erratum: Fiber-level Woven Fabric Capture from a Single Microscopic Image

A correction has been issued for the 2026 TOG paper on fiber-level woven fabric capture from a single microscopic image. For graphics teams working on materials, the practical takeaway is …

Zixuan LiPengfei ShenHanxiao SunZibo ZhangYu GuoLigang LiuLingqi YanSteve MarschnerMiloš HašanBeibei Wang ·
graphics materials fabric erratum academic-research
News

RealMat: Realistic Materials with Diffusion and Reinforcement Learning

RealMat combines Stable Diffusion XL with reinforcement learning to generate more believable material maps for 3D authoring. The pipeline starts from synthetic 2×2 material grids, then pushes the...

Xilong Zhou, Pedro Figueiredo, Milo\v{s} Ha\v{s}an, Valentin Deschaintre, Paul Guerrero, Yiwei Hu, Nima Khademi Kalantari ·
graphics materials diffusion-models reinforcement-learning procedural-content
News

A Hybrid Neural-Microfacet BRDF Model for Real-Time Rendering

A new hybrid BRDF aims to give real-time rendering a better middle ground between classic microfacet shading and heavier neural appearance models. By pairing a GGX-style base with a small …

Louis De Oliveira, Anastasia Karpova, Georges Nader, Antoine Houdard, Pierre Mezieres, Damien Rioux-Lavoie, Romain Pacanowski ·
graphics brdf neural rendering real-time rendering materials
News

Fiber-level Woven Fabric Capture from a Single Microscopic Image

A single microscopic image can now be used to reconstruct woven fabric at fiber-level detail, which is a big deal for material-heavy rendering pipelines. For teams chasing believable cloth, this...

Zixuan LiPengfei ShenHanxiao SunZibo ZhangYu GuoLigang LiuLingqi YanSteve MarschnerMiloš HašanBeibei Wang ·
research graphics materials fabric texture-capture
News

Neural Texture Compression using Hypernetworks

A new hypernetwork-based texture compressor can generate both latent texture features and decoder weights in one shot, avoiding per-material gradient descent. For graphics teams, the interesting part...

Belcour Laurent ·
graphics ai neural texture compression hypernetwork materials
News

Toward Richer Material Generation via Procedural Data Enhancement

This paper tackles a real bottleneck for material-generation workflows: training data that only covers simple diffuse-plus-single-specular PBR assets. The authors procedurally upgrade those materials...

Yunchen Yu, Jacob Munkberg, Jon Hasselgren, Chris Cummings, Steve Marschner, Andrea Weidlich ·
graphics materials ai neural-representation diffusion-models
News

HiMat: DiT-based Ultra-High Resolution SVBRDF Generation

HiMat tackles a real bottleneck for material authoring: generating 4K SVBRDFs without blowing up memory or losing map alignment. It uses a high-compression latent space plus a diffusion transformer...

Zixiong Wang, Jian Yang, Yiwei Hu, Milos Hasan, Beibei Wang ·
svbrdf materials diffusion texture generation technical art
News

Sine Waves - Procedural GPU Patterns

Procedural GPU patterns can look elegant, but they trade texture fetches for extra math and shader cost. Sine-wave based effects are a good example: they’re flexible, yet more complex patterns …

Catlike Coding Godot ·
graphics shaders ai performance materials
News

Spectral Rendering Without a Spectral Renderer: Learned Spectral Codes for RGB Pipelines

arXiv cs.GR details a learned spectral-code system that lets RGB renderers carry spectral data without changing the pipeline. The method targets the usual pain points—metamerism, colored glass,...

Jiaqi Yu (University of York), Dar'ya Guarnera (University of York), Giuseppe Claudio Guarnera (University of York, Lumirithmic Ltd) ·
graphics spectral rendering rgb pipeline materials lighting
News

VideoNeuMat: Neural Material Extraction from Generative Video Models

A paper from arXiv shows a 2-stage way to turn video diffusion models into reusable neural materials. The interesting part for game teams is that it uses 17 generated frames …

Bowen Xue, Saeed Hadadan, Zheng Zeng, Fabrice Rousselle, Zahra Montazeri, Milos Hasan ·
graphics materials neural rendering generative video technical art

Page 1 of 2