Joshua Rego

Papers

Total Citations

H-Index

About

Joshua Rego is a researcher at the intersection of computational imaging and robotic perception, whose work bridges the gap between traditional camera hardware and modern machine learning. His primary research areas include image restoration, sensor quantization analysis, and visual simultaneous localization and mapping (SLAM). Rego’s most notable contribution, "Deep camera obscura: an image restoration pipeline for pinhole photography" (2022, 9 citations), demonstrates how deep learning can enhance image quality for non-traditional camera systems, extending advances in low-light denoising, HDR imaging, and demosaicing beyond conventional lens-based cameras. His earlier work, "Analyzing Sensor Quantization Of Raw Images For Visual SLAM" (2020, 7 citations), critically examines how standard image sensor processing pipelines—optimized for human viewing—degrade performance in robotic navigation tasks. By showing that raw, minimally processed images can improve SLAM accuracy on low-power devices, Rego has provided a foundational insight for deploying efficient autonomous systems. His research is particularly impactful for mobile robotics and computational photography communities, offering practical pathways to enhance both consumer imaging and machine vision.