RGB-D Kitchen Dataset
Paired RGB and depth video from real kitchen environments with registered depth maps and 3D annotations for training depth-aware kitchen robots.
Dataset at a Glance
Comparison with Public Datasets
How Claru's dataset compares to publicly available alternatives.
| Dataset | Clips | Hours | Modalities | Environments | Annotations |
|---|---|---|---|---|---|
| ScanNet | 1.5K scans | ~5 | RGB-D | 707 rooms | 3D segmentation |
| NYU Depth V2 | 1.4K | ~2 | RGB-D | 464 scenes | Depth, segmentation |
| Claru RGB-D Kitchen | 50K+ | 350+ | RGB-D | 30+ kitchens | Depth, 3D reconstruction, objects, surfaces |
Use Cases
Depth-Aware Manipulation
Using depth for reach planning and collision avoidance in cluttered kitchens. Example models: UniDepth, DepthAnything, ICP grasping.
3D Scene Understanding
Building 3D kitchen representations for spatial reasoning. Example models: ScanNet++, Habitat, iGibson.
Transparent Object Detection
Using depth discontinuities to detect glass and clear objects. Example models: ClearGrasp, TransCG, Dex-NeRF.
Key References
- [1]Dai et al.. “ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes.” CVPR 2017, 2017. Link
- [2]Yang et al.. “Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data.” CVPR 2024, 2024. Link
- [3]Sajjan et al.. “ClearGrasp: 3D Shape Estimation of Transparent Objects.” ICRA 2020, 2020. Link
How Claru Delivers This Data
Claru captures synchronized RGB-D data using Intel RealSense cameras with factory-calibrated registration. Kitchen-specific depth data captures challenging geometry: reflective steel, transparent glass, and steam.
Frequently Asked Questions
Intel RealSense D435/D455 at 848x480 depth, synchronized with 1920x1080 RGB at 30fps.
Processing flags low-confidence depth regions and provides confidence maps. Transparent objects get supplementary boundary annotations.
Yes. Camera parameters enable point cloud generation and TSDF reconstruction. Pre-computed meshes available for a subset.
Request a Sample Pack
Get a curated sample of rgb-d kitchen data with full annotations to evaluate for your project.