Synthetic Dataset Generation and Validation for Robotic Surgery Instrument Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910022942851072 |
|---|---|
| author | Chiesa, Giorgio Borra, Rossella Lauro, Vittorio De Cillis, Sabrina Amparore, Daniele Fiori, Cristian Renzulli, Riccardo Grangetto, Marco |
| author_facet | Chiesa, Giorgio Borra, Rossella Lauro, Vittorio De Cillis, Sabrina Amparore, Daniele Fiori, Cristian Renzulli, Riccardo Grangetto, Marco |
| contents | This paper presents a comprehensive workflow for generating and validating a synthetic dataset designed for robotic surgery instrument segmentation. A 3D reconstruction of the Da Vinci robotic arms was refined and animated in Autodesk Maya through a fully automated Python-based pipeline capable of producing photorealistic, labeled video sequences. Each scene integrates randomized motion patterns, lighting variations, and synthetic blood textures to mimic intraoperative variability while preserving pixel-accurate ground truth masks. To validate the realism and effectiveness of the generated data, several segmentation models were trained under controlled ratios of real and synthetic data. Results demonstrate that a balanced composition of real and synthetic samples significantly improves model generalization compared to training on real data only, while excessive reliance on synthetic data introduces a measurable domain shift. The proposed framework provides a reproducible and scalable tool for surgical computer vision, supporting future research in data augmentation, domain adaptation, and simulation-based pretraining for robotic-assisted surgery. Data and code are available at https://github.com/EIDOSLAB/Sintetic-dataset-DaVinci. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13844 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Synthetic Dataset Generation and Validation for Robotic Surgery Instrument Segmentation Chiesa, Giorgio Borra, Rossella Lauro, Vittorio De Cillis, Sabrina Amparore, Daniele Fiori, Cristian Renzulli, Riccardo Grangetto, Marco Computer Vision and Pattern Recognition This paper presents a comprehensive workflow for generating and validating a synthetic dataset designed for robotic surgery instrument segmentation. A 3D reconstruction of the Da Vinci robotic arms was refined and animated in Autodesk Maya through a fully automated Python-based pipeline capable of producing photorealistic, labeled video sequences. Each scene integrates randomized motion patterns, lighting variations, and synthetic blood textures to mimic intraoperative variability while preserving pixel-accurate ground truth masks. To validate the realism and effectiveness of the generated data, several segmentation models were trained under controlled ratios of real and synthetic data. Results demonstrate that a balanced composition of real and synthetic samples significantly improves model generalization compared to training on real data only, while excessive reliance on synthetic data introduces a measurable domain shift. The proposed framework provides a reproducible and scalable tool for surgical computer vision, supporting future research in data augmentation, domain adaptation, and simulation-based pretraining for robotic-assisted surgery. Data and code are available at https://github.com/EIDOSLAB/Sintetic-dataset-DaVinci. |
| title | Synthetic Dataset Generation and Validation for Robotic Surgery Instrument Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.13844 |