Publication

Learning stereo reconstruction with deep neural networks

Publications associées (471)

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search

Deep(ly) Learning the Depth

Xun Victor Suo

We report on the use of deep learning algorithms to perform depth recovery in multiview imaging. We show that if enough training data are provided, a neural network such as multilayer perceptron can be trained to recover the depth in multiview imaging as a ...

2016

Theory of representation learning in cortical neural networks

Carlos Stein Naves de Brito

Our brain continuously self-organizes to construct and maintain an internal representation of the world based on the information arriving through sensory stimuli. Remarkably, cortical areas related to different sensory modalities appear to share the same f ...

EPFL2016

Real-Time Computational Gigapixel Multi-Camera Systems

Vladan Popovic

The standard cameras are designed to truthfully mimic the human eye and the visual system. In recent years, commercially available cameras are becoming more complex, and offer higher image resolutions than ever before. However, the quality of conventional ...

EPFL2016

EMVS: Event-based Multi-View Stereo

Davide Scaramuzza

Event cameras are bio-inspired vision sensors that output pixel-level brightness changes instead of standard intensity frames. They offer significant advantages over standard cameras, namely a very high dynamic range, no motion blur, and a latency in the o ...

2016

Modern techniques and applications for real-time non-rigid registration

Mark Pauly, Hao Li, Sofien Bouaziz, Andrea Tagliasacchi

Registration algorithms are an essential component of many computer graphics and computer vision systems. With recent technological advances in RGBD sensors (color plus depth), an active area of research is in techniques combining color, geometry, and lear ...

2016

Hardware Implementation and Applications of High Performance Multiple Camera Architectures

Kerem Seyid

Advancements in imaging technology made commercially available cameras cheaper, easily accessible with higher resolution than ever and with complex image capturing features. Today, it is estimated that more than one billion cameras sold every year. However ...

EPFL2016

Built-in Foreground/Background Prior for Weakly-Supervised Semantic Segmentation

Mathieu Salzmann, Fatemehsadat Saleh

Pixel-level annotations are expensive and time consuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recently, CNN-based methods have proposed to fine-tune pre-trained networks using im ...

Springer Int Publishing Ag2016

Using Deep Learning for Image-Based Plant Disease Detection

Marcel Salathé, Sharada Prasanna Mohanty

Crop diseases are a major threat to food security, but their rapid identification remains difficult in many parts of the world due to the lack of the necessary infrastructure. The combination of increasing global smartphone penetration and recent advances ...

Frontiers Media Sa2016

Tensor low-rank and sparse light field photography

Pierre Vandergheynst, Mahdad Hosseini Kamal

High-quality light field photography has been one of the most difficult challenges in computational photography. Conventional methods either sacrifice resolution, use multiple devices, or require multiple images to be captured. Combining coded image acquis ...

Elsevier2016

Image Inpainting through Neural Networks Hallucinations

Pascal Frossard, Alhussein Fawzi

We consider in this paper the problem of image inpainting, where the objective is to reconstruct large continuous regions of missing or deteriorated parts of an image. Traditional inpainting algorithms are unfortunately not well adapted to handle such corr ...

Ieee2016