Efficient and Transferable Deep Visual Odometry

Università di Roma La Sapienza

Artificial Intelligence
Cycle: 42

Traditional visual odometry (VO) methods are typically classified into feature-based and appearance-based approaches (also known as direct methods). In feature-based methods, the problem may be formulated as a windowed bundle adjustment (WBA) – or solved without it – minimizing the reprojection error. In direct methods, the objective is to define a cost function that estimates the camera pose by minimizing the photometric error across pixels.
Recently, deep visual odometry (DVO) approaches arise and they can be divided into modular and end-to-end methods. In modular approaches, DL is introduced into specific VO sub-tasks (e.g. feature extraction, feature matching, optical flow estimation, depth estimation or semantic understanding), where neural networks are highly specialized while the rest of the pipeline relies on classical geometry-based solutions. End-to-end DL solutions, where all tasks are learning-based, often suffer from poor generalization due to limitations in training datasets and typically incur high computational costs.
The PhD research should investigate how deep learning could support large-scale VO applications in real-world environments, considering indoor/outdoor complex scenarios, featuring textureless environments and illumination changes.
The expected developments and outcomes of the PhD include:
– Identifying the optimal balance between accuracy and processing time when choosing between a modular, component-wise integration and an end-to-end solution, while accounting for generalization limitations
– Developing methods for computational compression (e.g., neural network pruning, quantization, or distillation)
– Addressing the issue of poor generalization in deep learning by favouring local formulations (such as keypoint extraction and matching) that are inherently more transferable across environments
– Leveraging the retraining capabilities offered by the simulated environment of the ESA VAIPOSA project and studying how models trained in simulation can be effectively generalized to real-world datasets.
The ideal candidate should have an attitude towards problem-solving using programming environments, a strong background in AI and knowledge of robotics problems.

FBK Contact

Are you ready to join FBK international community?

We welcome motivated applicants who are passionate about research, eager to learn, and driven by curiosity to explore new ideas.

Six reasons to become a PhD student at FBK

At FBK, our PhD program is designed to develop highly specialized researchers in a unique, stimulating environment

RESEARCH
AT FBK​

A Hub of innovation and collaboration​

TOWARD PHD EXCELLENCE

FBK stands out as one of Italy’s leading research institutions

international
network

National and international
companies and universities

learning opportunities

Explore a world of learning
at FBK

Discover Trento

One of the most Italy’s
livable city

Join FBK

A truly international
community