Deep learning models can nowadays teach a machine to realize a number of tasks, even with better precision than human beings. Among all the modules of an intelligent machine, perception is the most essential part without which all other action modules have difficulties in safely and precisely realizing the target task under complex scenes. Conventional perception systems are based on RGB images which provide rich texture information about the 3D scene. However, the quality of RGB images highly depends on environmental factors, which further influence the performance of deep learning models. Therefore, in this thesis, we aim to improve the performance and robustness of RGB models with complementary depth cues by proposing novel RGB-D fusion ...
© 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...
Depth estimation from a single image is a key instrument for several applications from robotics to v...
Representing images in robust, discriminative and informative features is deemed to be crucial for g...
Les modèles d'apprentissage profond peuvent aujourd'hui faire apprendre une machine à réaliser un ce...
Multi-modal visual data can provide different information about the same scene, thus enhancing the a...
International audienceEfficiently exploiting multi-modal inputs for accurate RGB-D saliency detectio...
International audienceRGB-D saliency detection aims to fuse multi-modal cues to accurately localize ...
The existing saliency detection models based on RGB colors only leverage appearance cues to detect s...
Abstract Recently proposed state-of-the-art saliency detection models rely heavily on labeled datase...
Visual tracking performance has long been limited by the lack of better appearance models. These mod...
6D object pose estimation plays a crucial role in robotic manipulation and grasping tasks. The aim t...
This paper investigates the value of depth modality in object classification in RGB-D images. We use...
Salient Object Detection is the task of predicting the human attended region in a given scene. Fusin...
This thesis focuses on the “simultaneous acquisition of geometry and reflectance”. RGB-D cameras are...
RGB-D data has turned out to be a very useful representation for solving fundamental computer visio...
© 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...
Depth estimation from a single image is a key instrument for several applications from robotics to v...
Representing images in robust, discriminative and informative features is deemed to be crucial for g...
Les modèles d'apprentissage profond peuvent aujourd'hui faire apprendre une machine à réaliser un ce...
Multi-modal visual data can provide different information about the same scene, thus enhancing the a...
International audienceEfficiently exploiting multi-modal inputs for accurate RGB-D saliency detectio...
International audienceRGB-D saliency detection aims to fuse multi-modal cues to accurately localize ...
The existing saliency detection models based on RGB colors only leverage appearance cues to detect s...
Abstract Recently proposed state-of-the-art saliency detection models rely heavily on labeled datase...
Visual tracking performance has long been limited by the lack of better appearance models. These mod...
6D object pose estimation plays a crucial role in robotic manipulation and grasping tasks. The aim t...
This paper investigates the value of depth modality in object classification in RGB-D images. We use...
Salient Object Detection is the task of predicting the human attended region in a given scene. Fusin...
This thesis focuses on the “simultaneous acquisition of geometry and reflectance”. RGB-D cameras are...
RGB-D data has turned out to be a very useful representation for solving fundamental computer visio...
© 20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for a...
Depth estimation from a single image is a key instrument for several applications from robotics to v...
Representing images in robust, discriminative and informative features is deemed to be crucial for g...