MatSynth: A Modern PBR Materials Dataset
Giuseppe Vecchio, Valentin Deschaintre
Abstract
We introduce MatSynth, a dataset of 4, 000+ CCO ultra-high resolution PBR materials. Materials are crucial components of virtual relightable assets, defining the interaction of light at the surface of geometries. Given their importance, significant research effort was dedicated to their representation, creation, and acquisition. However, in the past 6 years, most research in material acquisition or gen-eration relied either on the same unique dataset, or on company-owned huge library of procedural materials. With this dataset, we propose a significantly larger, more di-verse, and higher resolution set of materials than previously publicly available. We carefully discuss the data collection process and demonstrate the benefits of this dataset for material acquisition and generation applications. The complete data further contains metadata with each mate-rial's origin, license, category, tags, creation method, and, when available, descriptions and physical size, as well as 3M+ renderings of the augmented materials, in lK, under various environment lightings. The MatSynth dataset is released through the project page at: https://www.gvecchio.com/matsynth.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers20
- Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic MaterialsYe Fang, Zeyi Sun, Tong Wu, Jiaqi Wang et al.NeurIPS 2024 · 21 citations
- LuxDiT: Lighting Estimation with Video Diffusion TransformerRuofan Liang, Kai He, Zan Gojcic, Igor Gilitschenski et al.NeurIPS 2025 · 20 citations
- Light of Normals: Unified Feature Representation for Universal Photometric StereoHouyuan Chen, Hong Li, Chongjie Ye, Zhaoxi Chen et al.ICLR 2026 · 12 citations
- OLATverse: A Large-scale Real-world Object Dataset with Precise Lighting ControlXilong Zhou, Jianchun Chen, Pramod Rao, Timo Teufel et al.CVPR 2026 · 6 citations
- Monocular Normal Estimation via Shading Sequence EstimationZongrui Li, Xinhua Ma, Minghui Hu, Yunqing Zhao et al.ICLR 2026 · 3 citations
Builds on18
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Implicit ModelsJiaming Song, Chenlin Meng, Stefano ErmonICLR 2021 · 11,743 citations
- Exploring CLIP for Assessing the Look and Feel of ImagesJianyi Wang, Kelvin C. K. Chan, Chen Change LoyAAAI 2023 · 1,208 citations
- Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene UnderstandingMike Roberts, Jason Ramapuram, Anurag Ranjan, Atulit Kumar et al.ICCV 2021 · 633 citations
- Highlight-aware two-stream network for single-image SVBRDF acquisitionJie Guo, Shuichang Lai, Chengzhi Tao, Yuelong Cai et al.SIGGRAPH 2021 · 70 citations
Related papers
- PhotoMat: A Material Generator Learned from Single Flash PhotosXilong Zhou, Milos Hasan, Valentin Deschaintre, Paul Guerrero et al.SIGGRAPH 2023 · 31 citations
- MatPedia: A Universal Generative Foundation for High-Fidelity Material SynthesisDi Luo, Shuhui Yang, Mingxin Yang, Jiawei Lu et al.CVPR 2026 · 3 citations
- Relightable Neural Human Assets from Multi-view Gradient IlluminationsTaotao Zhou, Kai He, Di Wu, Teng Xu et al.CVPR 2023
- HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View SynthesisTimo Teufel, Pulkit Gera, Xilong Zhou, Umar Iqbal et al.ICCV 2025 · 1 citation
- MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material ModelsMichael Birsak, John Femiani, Biao Zhang, Peter WonkaSIGGRAPH 2025 · 2 citations
