TY - GEN
T1 - Generative Compression
AU - Santurkar, Shibani
AU - Budden, David
AU - Shavit, Nir
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/9/5
Y1 - 2018/9/5
N2 - Traditional image and video compression algorithms rely on hand-crafted encoder/decoder pairs (codecs) that lack adaptability and are agnostic to the data being compressed. We describe the concept of generative compression, the compression of data using generative models, and suggest that it is a direction worth pursuing to produce more accurate and visually pleasing reconstructions at deeper compression levels for both image and video data. We also show that generative compression is orders- of-magnitude more robust to bit errors (e.g., from noisy channels) than traditional variable-length coding schemes.
AB - Traditional image and video compression algorithms rely on hand-crafted encoder/decoder pairs (codecs) that lack adaptability and are agnostic to the data being compressed. We describe the concept of generative compression, the compression of data using generative models, and suggest that it is a direction worth pursuing to produce more accurate and visually pleasing reconstructions at deeper compression levels for both image and video data. We also show that generative compression is orders- of-magnitude more robust to bit errors (e.g., from noisy channels) than traditional variable-length coding schemes.
UR - http://www.scopus.com/inward/record.url?scp=85053865136&partnerID=8YFLogxK
U2 - 10.1109/PCS.2018.8456298
DO - 10.1109/PCS.2018.8456298
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85053865136
SN - 9781538641606
T3 - 2018 Picture Coding Symposium, PCS 2018 - Proceedings
SP - 258
EP - 262
BT - 2018 Picture Coding Symposium, PCS 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 33rd Picture Coding Symposium, PCS 2018
Y2 - 24 June 2018 through 27 June 2018
ER -