Multi-view multi-light HDR captures of cloth materials with associated 3D geometry, designed for inverse rendering and BRDF estimation. The dataset contains 500 materials, totaling 3.62 TB across 9,853 files, and was created by koalapenguin. It was last updated on 2026-05-03.
Use Cases
- Estimate Bidirectional Reflectance Distribution Functions (BRDFs) based on multi-view multi-light HDR captures.
- Train inverse rendering models based on the associated 3D geometry and material captures.
- Benchmark material appearance modeling algorithms based on the provided cloth samples.
- Develop novel rendering techniques based on the high-dynamic-range (HDR) image data.
Strengths
- Contains 500 distinct cloth material samples.
- Total data volume is 3.62 TB (3,622 GB) across 9,853 files, indicating substantial detail.
- Includes associated 3D geometry for the captured materials.
- Provides a sample subset (≤4 GB) for preliminary inspection.
Limitations
- Column-level documentation is absent; field semantics must be inferred after download.
- Row count is unknown, which may limit suitability assessment.
- Last updated 2026-05-03 11:07:38; freshness should be verified.
Provenance
- Source
- huggingface
- Collection Method
- Multi-view multi-light HDR capture.
- Freshness
- 2026-05-03 11:07:38