Matthew Grech‐Sollars

University College London

Papers

1

Total Citations

4

H-Index

1

About

Matthew Grech-Sollars is pioneering the integration of foundation models into robotic-assisted surgery (RAS), with a focus on depth estimation for 3D reconstruction and visualization. His most-cited work, "DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model" (2025, 4 citations), addresses a critical bottleneck: directly applying general-purpose depth models like Depth Anything Models (DAM) to surgical domains often fails due to domain shift. Grech-Sollars introduces a self-supervised Vector-LoRA approach that efficiently adapts these large models to limited surgical data without catastrophic forgetting, enabling accurate, real-time depth perception in endoscopic scenes. This contribution is vital for improving surgical precision, autonomy, and safety in RAS. His work sits at the intersection of computer vision, transfer learning, and medical robotics, demonstrating how parameter-efficient fine-tuning can unlock foundation models for specialized, high-stakes environments. Though early in citation impact, the novelty and timeliness of DARES signal a growing influence, positioning Grech-Sollars as a rising figure in surgical AI.

Research Focus

Key Achievements

1
H-Index
1
Papers
4
Total Citations
4
Avg Citations/Paper
🏆 Most Cited Paper
DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model
4 citations · 2025
📈 Most Prolific Year: 2025 (1 Papers)
🤝 Key Collaborators: 13
🏛 Institutions: University College London

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago