Datasets › Vastextures

Vastextures (Vast Dataset for textures and PBR materials)

Introduced by Sagi Eppel et al. in Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data5 Mar 2024 archive 2025-07-28

VasTexture is a free giant repository of textures and PBR materials extracted from real-world images. The repository contains 500,000 highly diverse textures and PBR materials. All assets are free to download and use. The PBR materials and textures were extracted from natural images using an unsupervised approach (no human intervention). As a result, the textures and PBR materials are significantly more diverse but also significantly less refined compared to assets made using manual and AI approaches.

Benchmarks archive 2025-07-28

No leaderboard in the archive resolves to this dataset.

Papers archive 2025-07-28

No paper in the archive has a leaderboard row on this dataset; the archive counts 1 paper for it but never published that list.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

No task tagged in the archive.

License archive 2025-07-28

CC0

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • Vastextures

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections