by Martina Megaro | Jun 27, 2018 | Machine Learning, Robotics
Automated Deep Reinforcement Learning Environment for Hardware of a Modular Legged Robot We present an automated learning environment for developing control policies directly on the hardware of a modular legged robot. June 27, 2018International Conference on...
by Martina Megaro | Jun 18, 2018 | Video Processing, Visual Computing
Normalized Cut Loss for Weakly-supervised CNN Segmentation Our normalized cut loss approach to segmentation brings the quality of weakly-supervised training significantly closer to fully supervised methods. June 18, 2018IEEE Conference on Computer Vision Pattern...
by Martina Megaro | Jun 18, 2018 | Video Processing, Visual Computing
PhaseNet for Video Frame Interpolation We propose a new approach, PhaseNet, that is designed to robustly handle challenging scenarios while also coping with larger motion. June 18, 2018IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2018 Authors...
by Martina Megaro | Jun 18, 2018 | Video Processing, Visual Computing
A Progressive Approach to Single-Image Super-Resolution We propose a method (ProSR) that is progressive both in architecture and training: the network upsamples an image in intermediate steps, while the learning process is organized from easy to hard, as is done in...
by Martina Megaro | Jun 5, 2018 | Robotics
Computational Co-Optimization of Design Parameters and Motion Trajectories for Robotic Systems We present a novel computational approach to optimizing the morphological design of robots. June 5, 2018International Journal of Robotics Research 2018 Authors...
