In this thesis we aim at analyzing images and videos at the object level, with the goal of decomposing the scene into complete objects that move and interact among themselves. The thesis is divided in three parts. First, we propose a segmentation method to decompose the scene into shapes. Then, we propose a probabilistic method, which works with shapes or objects at two different depths, to infer which objects are in front of the others, while completing the ones which are partially occluded. Finally, we propose two video related inpainting method. On one hand, we propose a binary video inpainting method that relies on the optical flow of the video in order to complete the shapes across time taking into account their motion. On the other hand...
In this paper we propose an interactive method for the segmen-tation of objects in video. We aim to ...
Automatic video object segmentation based on spatial-temporal information has been a research topic ...
We present a novel approach to moving object detec-tion in video taken from a translating, rotating ...
In this thesis we aim at analyzing images and videos at the object level, with the goal of decomposi...
We present a method to estimate the relative depth between objects in scenes of video sequences. The...
Information In the paper we present a method to estimate relative depth between objects in scenes of...
In this paper two efficient unsupervised video object segmentation approaches are proposed and then ...
The objective of this Thesis research is to develop algorithms for temporally consistent semantic se...
We present a method to decompose video sequences into layers that represent the relative depths of c...
We describe an approach for segmenting an image into regions that correspond to surfaces in the scen...
Occlusions and disocclusions are essential cues for human perception in understanding the layout of ...
This study presents a segmentation pipeline that fuses colour and depth information to automatically...
This thesis describes a framework leveraging occlusions as a cue for detecting objects and accuratel...
A fundamental goal of computer vision is the ability to detect and track semantic objects. This can ...
We present an unsupervised approach for learning a layered representation of a scene from a video fo...
In this paper we propose an interactive method for the segmen-tation of objects in video. We aim to ...
Automatic video object segmentation based on spatial-temporal information has been a research topic ...
We present a novel approach to moving object detec-tion in video taken from a translating, rotating ...
In this thesis we aim at analyzing images and videos at the object level, with the goal of decomposi...
We present a method to estimate the relative depth between objects in scenes of video sequences. The...
Information In the paper we present a method to estimate relative depth between objects in scenes of...
In this paper two efficient unsupervised video object segmentation approaches are proposed and then ...
The objective of this Thesis research is to develop algorithms for temporally consistent semantic se...
We present a method to decompose video sequences into layers that represent the relative depths of c...
We describe an approach for segmenting an image into regions that correspond to surfaces in the scen...
Occlusions and disocclusions are essential cues for human perception in understanding the layout of ...
This study presents a segmentation pipeline that fuses colour and depth information to automatically...
This thesis describes a framework leveraging occlusions as a cue for detecting objects and accuratel...
A fundamental goal of computer vision is the ability to detect and track semantic objects. This can ...
We present an unsupervised approach for learning a layered representation of a scene from a video fo...
In this paper we propose an interactive method for the segmen-tation of objects in video. We aim to ...
Automatic video object segmentation based on spatial-temporal information has been a research topic ...
We present a novel approach to moving object detec-tion in video taken from a translating, rotating ...