lu.se

Kommunikationsteknikportalen

Lunds Tekniska Högskola

Denna sida på svenska This page in English

Kalender

Här hittar du samlade händelser framöver inom LTHs tekniska och naturvetenskapliga områden, många med bäring på kommunikationsteknik. Till höger har du direktlänk till kalendern för Elektro- och Informationsteknik.

Kalendarium för kommunikationsteknik

Deep Learning Methods for Streaming Image Reconstruction in Fixed-camera Settings

Seminarium

Tid: 2017-12-18 10:15 till: 11:00
Plats:MBN:333 Matematikhuset
Kontakt:Lars.Eklundh@nateko.lu.se


Johan Förberg, presenterar sitt examensarbete

ABSTRACT

A streaming video reconstruction system is described and implemented as a convolutional neural network. The system performs combined 2x super-resolution and H.264 artefacts removal with a processing speed of about 6 frames per second at 1920×1080 output resolution on current workstation-grade hardware. In 4x super-resolution mode, the system can output 3840 × 2160 video at a similar rate. The base system provides quality improvements of 0.010–0.025 SSIM over tradtional Lanczos filtering. Scene-specific training, in which the system automatically adapts to the current scene viewed by the camera, is shown to achieve up to 0.030 SSIM additional improvement in some scenarios. It is further shown that scene-specific training can provide some improvement even when reconstructing an unfamiliar scene, as long as the camera and capture settings remain the same.

Disputationer

Följande disputationer är på gång:

 

27 Nov: Iman Vakili. Opponent: Prof. Andrea Neto