47 citations · 131 across the 26 of their papers we have counts for
5 papers · 1 filter
Improving Optical Flow on a Pyramid Level
Markus Hofinger, Samuel Rota Bulò, Lorenzo Porzi +3
In this work we review the coarse-to-fine spatial feature pyramid concept, which is used in state-of-the-art optical flow estimation networks to make exploration of the pixel flow…
Towards Generalization Across Depth for Monocular 3D Object Detection
Andrea Simonelli, Samuel Rota Bulò, Lorenzo Porzi +2
While expensive LiDAR and stereo camera rigs have enabled the development of successful 3D object detection methods, monocular RGB-only approaches lag much behind. This work advanc…
Learning Multi-Object Tracking and Segmentation from Automatic Annotations
Lorenzo Porzi, Markus Hofinger, Idoia Ruiz +3
In this work we contribute a novel pipeline to automatically generate training data, and to improve over state-of-the-art multi-object tracking and segmentation (MOTS) methods. Our…
Disentangling Monocular 3D Object Detection
Andrea Simonelli, Samuel Rota Rota Bulò, Lorenzo Porzi +2
In this paper we propose an approach for monocular 3D object detection from a single RGB image, which leverages a novel disentangling transformation for 2D and 3D detection losses…
Seamless Scene Segmentation
Lorenzo Porzi, Samuel Rota Bulò, Aleksander Colovic +1
In this work we introduce a novel, CNN-based architecture that can be trained end-to-end to deliver seamless scene segmentation results. Our goal is to predict consistent semantic…