Omprakash Jha

Papers

Total Citations

H-Index

About

Omprakash Jha is a researcher advancing the field of computer vision, with a primary focus on unsupervised deep learning for monocular depth estimation. His most cited work, "Unsupervised Depth and Confidence Prediction from Monocular Images using Bayesian Inference" (2020, 7 citations), introduces a novel framework that leverages Bayesian inference to enhance per-pixel depth accuracy from single RGB images. By jointly predicting depth, pose, and a confidence map, Jha’s approach addresses a critical challenge in autonomous systems: reliable depth perception without costly labeled data. This contribution is particularly impactful for applications in robotics, autonomous driving, and 3D scene understanding, where robust uncertainty quantification is essential. Jha’s research demonstrates a keen ability to integrate probabilistic reasoning with deep learning, offering a principled method for improving prediction reliability. While his citation count is modest, the work represents a meaningful step toward safer and more interpretable vision systems. His ongoing efforts continue to explore the intersection of unsupervised learning and Bayesian methods, positioning him as a thoughtful contributor to the next generation of perception algorithms.