3DReflecNet: A Large-Scale Synthetic Dataset for Reflective and Transparent Objects

3DReflecNet is a large-scale synthetic multi-view dataset for novel view synthesis and 3D reconstruction. It provides Blender-rendered RGB images, masks, depth maps, normal maps, camera parameters, and 3D model assets. The dataset was created by 3DReflecNet and last updated on Hugging Face in June 2026.

Use Cases

• Train novel view synthesis models based on multi-view RGB images and camera parameters.
• Develop 3D reconstruction algorithms for reflective objects using depth and normal maps.
• Benchmark material segmentation models using provided material and environment annotations.
• Generate synthetic training data for textureless object detection and segmentation tasks.

Strengths

• Dataset is described as large-scale, suggesting a substantial number of samples.
• Provides multiple aligned data modalities including RGB images, masks, depth maps, normal maps, and camera parameters.
• Includes 3D model assets and material annotations, enabling detailed analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and total dataset size are unknown, which may limit suitability assessment.
• Data is synthetic, which may limit generalizability to real-world scenarios.

Provenance

Source

3DReflecNet

Collection Method

Synthetically generated using Blender rendering.

Freshness

Last updated 2026-06-04 11:13:15.