Learning Raw Image Reconstruction-Aware Deep Image Compressors

Deep learning-based image compressors are actively being explored in an effort to supersede conventional image compression algorithms, such as JPEG. Conventional and deep learning-based compression algorithms focus on minimizing image fidelity errors in the nonlinear standard RGB (sRGB) color space....

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence Jg. 42; H. 4; S. 1013 - 1019
Hauptverfasser: Punnappurath, Abhijith, Brown, Michael S.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States IEEE 01.04.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Accuracy
Algorithms
Calibration
Cameras
Compressors
Computer vision
Deep learning
deep learning-based image compression
Image coding
Image compression
Image reconstruction
JPEG encoders-decoders
Machine learning
radiometric calibration
raw image reconstruction
Table lookup
Transform coding
ISSN:0162-8828, 1939-3539, 2160-9292, 1939-3539
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Deep learning-based image compressors are actively being explored in an effort to supersede conventional image compression algorithms, such as JPEG. Conventional and deep learning-based compression algorithms focus on minimizing image fidelity errors in the nonlinear standard RGB (sRGB) color space. However, for many computer vision tasks, the sensor's linear raw-RGB image is desirable. Recent work has shown that the original raw-RGB image can be reconstructed using only small amounts of metadata embedded inside the JPEG image [1]. However, [1] relied on the conventional JPEG encoding that is unaware of the raw-RGB reconstruction task. In this paper, we examine the ability of deep image compressors to be "aware" of the additional objective of raw reconstruction. Towards this goal, we describe a general framework that enables deep networks targeting image compression to jointly consider both image fidelity errors and raw reconstruction errors. We describe this approach in two scenarios: (1) the network is trained from scratch using our proposed joint loss, and (2) a network originally trained only for sRGB fidelity loss is later fine-tuned to incorporate our raw reconstruction loss. When compared to sRGB fidelity-only compression, our combined loss leads to appreciable improvements in PSNR of the raw reconstruction with only minor impact on sRGB fidelity as measured by MS-SSIM.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0162-8828
1939-3539
2160-9292
1939-3539
DOI:10.1109/TPAMI.2019.2903062