HyKey Dataset: A robotic-acquired dual-modality RGB-HSI Laparoscopic Dataset

DOI

The HyKey Dataset is the first publicly-released robotically-acquired dual-modality RGB and snapshot hyperspectral imaging (HSI) dataset. The images consist of ex-vivo ovine organs acquired through a laparoscope, collected to support keypoint detection and 3D reconstruction research in minimally invasive surgery (MIS).48 acquisitions were collected across seven ovine kidney sets (K1-K7) and three liver sets (L1-L3) under laparoscopic and surgical overhead lighting, following hemispherical-sweep and trocar (RCM) trajectories. Each acquisition provides 16-band snapshot HSI cubes (XIMEA MQ022HG-IM-SM4X4-VIS) and RGB frames, together with hand-eye-calibrated camera poses derived from a robotic arm end-effector, radiometric white/dark references, and pre-computed RGB-HSI registration homographies.The dataset is the training and evaluation benchmark for HyKey (Saikia et al., IJCARS 2026), where HSI-based keypoint detection outperformed HSI and RGB baselines, achieving 96.62% mean matching accuracy and 67.18% mAA@10° on pose estimation.Contents per acquisition: raw HSI mosaics (.npy), raw RGB frames (.npy), hsi_poses.csv, rgb_poses.csv, frame_log.csv, radiometric references, lighting and trajectory info.License: CC BY-NC 4.0. For commercial use, contact the authors.Code & model weights & Dataset Description: https://github.com/alexsaikia/HyKey-Hyperspectral-Keypoint-DetectionIf you use this dataset please cite the following articles:Paper for HyKey: https://link.springer.com/article/10.1007/s11548-026-03633-zPaper for Robotic Arm Acquisition Platform: https://ieeexplore.ieee.org/abstract/document/10879583

Identifier
DOI https://doi.org/10.5522/04/32793294.v1
Related Identifier HasPart https://ndownloader.figshare.com/files/66051458
Related Identifier HasPart https://ndownloader.figshare.com/files/66051461
Related Identifier HasPart https://ndownloader.figshare.com/files/66051464
Related Identifier HasPart https://ndownloader.figshare.com/files/66051467
Related Identifier HasPart https://ndownloader.figshare.com/files/66051470
Related Identifier HasPart https://ndownloader.figshare.com/files/66051740
Related Identifier HasPart https://ndownloader.figshare.com/files/66051788
Related Identifier HasPart https://ndownloader.figshare.com/files/66051791
Related Identifier HasPart https://ndownloader.figshare.com/files/66051794
Related Identifier HasPart https://ndownloader.figshare.com/files/66051797
Related Identifier HasPart https://ndownloader.figshare.com/files/66051800
Related Identifier HasPart https://ndownloader.figshare.com/files/66051803
Related Identifier HasPart https://ndownloader.figshare.com/files/66051806
Related Identifier HasPart https://ndownloader.figshare.com/files/66051809
Related Identifier HasPart https://ndownloader.figshare.com/files/66051812
Related Identifier HasPart https://ndownloader.figshare.com/files/66051815
Related Identifier HasPart https://ndownloader.figshare.com/files/66051818
Related Identifier HasPart https://ndownloader.figshare.com/files/66051821
Related Identifier HasPart https://ndownloader.figshare.com/files/66051824
Metadata Access https://api.figshare.com/v2/oai?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:figshare.com:article/32793294
Provenance
Creator Saikia, Alex ORCID logo; Di Vece, Chiara ORCID logo; Mao, Zhehua; Bonilla, Sierra; He, Chloe; Ramalhinho, Joao; Czempiel, Tobias ORCID logo; Bano, Sophia; Stoyanov, Danail
Publisher University College London UCL
Contributor Figshare
Publication Year 2026
Rights https://creativecommons.org/licenses/by-nc/4.0/; http://purl.org/coar/access_right/c_abf2
OpenAccess true
Contact researchdatarepository(at)ucl.ac.uk
Representation
Language English
Resource Type Dataset
Discipline Natural Sciences; Physics