BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T233530Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241121T100000
DTEND;TZID=America/New_York:20241121T170000
UID:submissions.supercomputing.org_SC24_sess534_post159@linklings.com
SUMMARY:Exploration of Super-Resolution Techniques for Image Compression
DESCRIPTION:Alexis Amoyo (RIKEN, Florida State University); Amarjit Singh 
 and Kento Sato (RIKEN); and Weikuan Yu (Florida State University)\n\nTEZIP
  is a (de)compression framework leveraging PredNet, a deep neural network 
 designed for video prediction tasks, to exploit temporal locality in time-
 evolving data. This study evaluates video super-resolution (VSR) models, w
 hich enhance low-resolution images by reconstructing high-resolution ones,
  under various compression and size reduction techniques. Specifically, we
  evaluate the VRT and BasicVSR++ models across various compression techniq
 ues, including H.264 and H.265, applied to the Vimeo90K dataset. Our resul
 ts, evaluated using common super-resolution image quality metrics, indicat
 e that the VRT model consistently outperforms BasicVSR++, particularly wit
 h H.264 and H.265 compressions. We observe that larger file sizes and lowe
 r compression ratios correlate with higher PSNR and SSIM values, highlight
 ing the trade-offs between compression techniques and quality metrics in g
 enerating high-resolution images. These findings emphasize the balance nee
 ded between compression efficiency and image quality in VSR applications.\
 n\nRegistration Category: Tech Program Reg Pass, Exhibits Reg Pass\n\nSess
 ion Chairs: Ayesha Afzal (Friedrich-Alexander University, Erlangen-Nurembe
 rg; Erlangen National High Performance Computing Center); Sally Ellingson 
 (University of Kentucky); and Alan Sussman (University of Maryland)\n\n
END:VEVENT
END:VCALENDAR