Author name cluster

Dragos Costea

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

2 author rows

ICRA Conference 2022 Conference Paper

UFO Depth: Unsupervised learning with flow-based odometry optimization for metric depth estimation

Vlad Licaret
Victor Robu
Alina Marcu
Dragos Costea
Emil Slusanschi
Rahul Sukthankar
Marius Leordeanu

We propose an efficient method for unsupervised learning of metric depth estimation from a single image in the context of unconstrained videos captured from UAVs. We combine the accuracy of an analytical solution based on odometry with the power of deep learning. First, we show how to correct the noisy odometric measurements by optimizing the alignment between the derotated optical flow and the projected linear speed in the image. Then, we detail an analytical depth estimation method based on optical flow and corrected camera velocities. Subsequently, the improved depth and camera veloc-ities obtained analytically are used, as additional cost terms, for training our novel unsupervised learning architecture for metric depth estimation. We extensively test on a recent UAV dataset, which we significantly extend by adding completely novel scenes. We outperform by significant margins different kinds of state-of-the-art approaches, ranging from analytical and unsupervised solutions to transformer-based architectures that require heavy computation and pre-training. The resulting algorithm could be deployed on embedded devices, being a good candidate for practical robotics use cases, such as obstacle avoidance and safe landing for UAV s.

Details

AAAI Conference 2021 Conference Paper

Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus

Marius Leordeanu
Mihai Cristian Pîrvu
Dragos Costea
Alina E Marcu
Emil Slusanschi
Rahul Sukthankar

We address the challenging problem of semi-supervised learning in the context of multiple visual interpretations of the world by finding consensus in a graph of neural networks. Each graph node is a scene interpretation layer, while each edge is a deep net that transforms one layer at one node into another from a different node. During the supervised phase edge networks are trained independently. During the next unsupervised stage edge nets are trained on the pseudo-ground truth provided by consensus among multiple paths that reach the nets’ start and end nodes. These paths act as ensemble teachers for any given edge and strong consensus is used for high-confidence supervisory signal. The unsupervised learning process is repeated over several generations, in which each edge becomes a ”student” and also part of different ensemble ”teachers” for training other students. By optimizing such consensus between different paths, the graph reaches consistency and robustness over multiple interpretations and generations, in the face of unknown labels. We give theoretical justifications of the proposed idea and validate it on a large dataset. We show how prediction of different representations such as depth, semantic segmentation, surface normals and pose from RGB input could be effectively learned through self-supervised consensus in our graph. We also compare to state-of-the-art methods for multi-task and semi-supervised learning and show superior performance.

PDF Details