Adaptive extreme video completion

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Situational awareness strategies are essential for the reliable and secure operation of the electric power grid which represents critical infrastructure in modern society. With the rise of converter-interfaced renewable generation and the consequent shift ...

Video DeepFakes are fake media created with Deep Learning (DL) that manipulate a person’s expression or identity. Most current DeepFake detection methods analyze each frame independently, ignoring inconsistencies and unnatural movements between frames. Som ...

The mission of WEST (tungsten-W Environment in Steady-state Tokamak) is to explore long pulse operation in a full tungsten (W) environment for preparing next-step fusion devices (ITER and DEMO) with a focus on testing the ITER actively cooled W divertor in ...

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

Reinterpretable cameras are defined by their post-processing capabilities that exceed traditional imaging. We present "SoDaCam" that provides reinterpretable cameras at the granularity of photons, from photon-cubes acquired by single-photon devices. Photon ...

In the present paper, we show, by means of numerical simulations, that electromagnetic field data obtained from the radiation of a return-stroke lightning discharge and measured over a short-duration time-window can be exploited to reconstruct the attenuat ...

Designing architectural façades that allow sufficient daylight to create visually comfortable and pleasant environments is a challenging aspect of building design. It requires accounting for visual comfort and discomfort glare risks and understanding the f ...

With the purpose of reducing the heating energy in buildings, it is common practice to install energy-efficient windows to increase the thermal insulation of a façade. These insulating glass units (IGIJ) include a thin silver coating acting as an infrared ...

In event-based sensing, many sensors independently and asynchronously emit events when there is a change in their input. Event-based sensing can present significant improvements in power efficiency when compared to traditional sampling, because (1) the out ...

In this paper, we introduce a new solution and underlying architecture that allows remote participants to interact with hosts in a broadcast scenario. To achieve this, background extraction is first applied to video received from remote participants to ext ...

In this paper, we propose and compare personalized models for Productive Engagement (PE) recognition. PE is defined as the level of engagement that maximizes learning. Previously, in the context of robot-mediated collaborative learning, a framework of prod ...

Modern media data such as 360 degrees videos and light field (LF) images are typically captured in much higher dimensions than the observers' visual displays. To efficiently browse high-dimensional media, a navigational streaming model is considered: a cli ...

Lightning causes significant damage and casualties globally by directly striking humans and livestock, by igniting forest fires, and by inducing electrical surges in electronic infrastructure, airplanes, rockets, etc. Monitoring the evolution of thundersto ...

As event-based sensing gains in popularity, theoretical understanding is needed to harness this technology’s potential. Instead of recording video by capturing frames, event-based cameras have sensors that emit events when their inputs change, thus encodin ...

Spatiotemporal features are integrated along motion trajectories. For example, when a central line is followed by pairs of flanking lines, two motion streams diverging from the center are perceived. The central line is rendered invisible by the subsequent ...

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

Daylight provision to the indoor space is affected by different building elements that cannot be fully controlled by the users, such as the window size of a space. The dimensions of the fenestration not only affect the lighting levels, but they also affect ...

A simulation model and an experimental characterization of energy saving glazing transparent to mobile communication frequency up to 40 GHz is presented. A previous study showed that laser structured energy efficient windows with a frequency selective surf ...

The size of window openings is widely acknowledged as an important factor in our spatial perception. However, little is known about how the perception and preference of windows changes between countries, leaving a gap of knowledge regarding the applicabili ...

We present a comprehensive analysis of the submissions to the first edition of the Endoscopy Artefact Detection challenge (EAD). Using crowd-sourcing, this initiative is a step towards understanding the limitations of existing state-of-the-art computer vis ...

Adaptive extreme video completion

Chat with Graph Search

Functional-Basis Analysis of Non-Stationary Signals in Modern Power Grids: Theory and Implementation in Embedded Systems

Efficient Temporally-Aware DeepFake Detection using H.264 Motion Vectors

WEST full tungsten operation with an ITER grade divertor

Aggregating Spatial and Photometric Context for Photometric Stereo

SoDaCam: Software-defined Cameras via Single-Photon Imaging

Computation of the attenuation function of the lightning return-stroke current from electromagnetic fields measured in a short-duration time-window — Part II: Numerical implementation

Discomfort glare from daylight: Influence of transmitted color and the eye's macular pigment

Combining thermal insulation and mobile communication in buildings: influence of laser-treated glazing on microwave propagation

Asynchrony Increases Efficiency: Time Encoding of Videos and Low-Rank Signals

AI-based telepresence for broadcast applications

Personalized Productive Engagement Recognition in Robot-Mediated Collaborative Learning

Landmarking for Navigational Streaming of Stored High-Dimensional Media

On the Use of Benford’s Law to Assess the Quality of the Data Provided by Lightning Locating Systems

How Asynchronous Events Encode Video

Visual feature integration: how long can it last?

Counting People by Estimating People Flows

Window Size Effects on Subjective Impressions of Daylit Spaces: Indoor Studies at High Latitudes Using Virtual Reality

Wide band-pass FSS with reduced periodicity for energy efficient windows at higher frequencies

Regional Differences in the Perception of Daylit Scenes across Europe Using Virtual Reality. Part I: Effects of Window Size

An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopy