Stereo Dataset: Synthetic Multiview Scenes with RGB and Depth Videos

StereoDataset is a synthetic multiview stereo dataset rendered in Unreal Engine. Each scene combines a map, a character mesh, an animation clip, a validated spawn location, and a camera trajectory. The dataset was created by 'stereo-dataset' and was last updated on the Hugging Face platform in May 2026.

Use Cases

• Training depth estimation models based on synchronized RGB and depth video pairs.
• Developing novel-view synthesis algorithms using the provided multiview camera trajectories.
• Benchmarking 3D scene reconstruction pipelines based on synthetic scenes with ground-truth geometry.
• Researching animation and character rendering in controlled, synthetic environments.

Strengths

• Provides synchronized per-camera RGB and depth videos, offering ground-truth geometry.
• Scenes are constructed from validated components including maps, character meshes, and animation clips.
• Includes scene-level metadata files for trajectory and baseline information.

Limitations

• Dataset size, row count, and specific file formats are unknown from the provided metadata.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is synthetic, which may limit applicability to real-world scenarios.

Provenance

Source

huggingface

Collection Method

Synthetically rendered in Unreal Engine.

Freshness

Last updated 2026-05-20 21:56:22; freshness should be verified.