LEMON: Large Endoscopic Monocular Video Dataset for Surgical Perception

LEMON is a large dataset of full FPS endoscopic monocular videos introduced in the paper 'LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings'. The dataset is hosted by the user 'visurg' on Hugging Face and was last updated on April 8, —. The repository provides the full video collection for download.

Use Cases

• Training foundation models for surgical scene understanding based on the described endoscopic video content.
• Developing and benchmarking monocular depth estimation algorithms for endoscopic procedures.
• Researching surgical instrument tracking and segmentation using real-world endoscopic footage.
• Creating synthetic data generation pipelines for surgical training simulations based on real video data.

Strengths

• Dataset is associated with a published academic paper, suggesting a research foundation.
• Last updated date is provided (2026-04-08 09:23:41), indicating recent maintenance.

Limitations

• Description metadata is limited; actual data quality, size, and format require manual inspection after download.
• Column-level documentation is absent; field semantics and video annotations must be inferred after download.
• Row count, file formats, and license information are unknown, which may limit suitability assessment.

Provenance

Source

visurg (Hugging Face user), associated with the LEMON research paper.

Collection Method

Likely collected from surgical endoscopic procedures, as described in the associated paper.

Time Range

null

Freshness

Last updated 2026-04 08 09:23:41.

Geography

null