There are multiple traditional geometric problems in computer vision such as camera pose estimation, 3D reconstruction depth estimation, and tracking for which strong mathematical models and efficient, robust algorithms have been known for decades. Recently with the popularity of deep learning, researchers have applied various deep neural networks models to almost all of these problems and demonstrated state of the art performance on the benchmark datasets. However, modern learning based techniques also have known shortcomings in terms of handling out of distribution situations and susceptibility to adversarial attacks. The objective of this project is to explore parametric deep neural networks, whereby a standard deep neural network is constrained to broadly follow the steps of a prescribed mathematical model with a scope for learning each of the individual step using the available data. The developed model should ideally have the flexibility of learning based techniques, and at the same time robustness and interpretability of conventional mathematical techniques.
The output of the PhD will be parametric deep neural network designs for multiple geometric computer vision problems. We will explore collaboration with industry partners working in the related areas for possible transfer of technology and application of the research output. For example, industry partners developing products for autonomous driving and advance driver assistance may be interested in such technology.
Computer Vision, Machine Learning.
Deep Learning.
An undergraduate or masters degree in computer science or electrical engineering.
An ideal student for this project will have an undergraduate or masters degree in Computer Science, or Electrical Engineering. The student would have done courses in computer vision and machine learning at undergraduate/masters level. He/she would have strong grip on mathematical fundamentals such linear algebra, and probability.