Snapshot High Dynamic Range Imaging via Sparse Representations and Feature Learning

Bracketed High Dynamic Range (HDR) imaging architectures acquire a sequence of Low Dynamic Range (LDR) images in order to either produce a HDR image or an "optimally" exposed LDR image, achieving impressive results under static camera and scene conditions. However, in real world conditions...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on multimedia Ročník 22; číslo 3; s. 688 - 703
Hlavní autoři: Fotiadou, Konstantina, Tsagkatakis, Grigorios, Tsakalides, Panagiotis
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.03.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Computer science
deep learning
Dynamic range
Exposure
High dynamic range imaging
Image acquisition
Image reconstruction
Imaging
Learning
Lighting
Optimization
sparse representations
sparse stacked autoencoders
Streaming media
ISSN:1520-9210, 1941-0077
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Bracketed High Dynamic Range (HDR) imaging architectures acquire a sequence of Low Dynamic Range (LDR) images in order to either produce a HDR image or an "optimally" exposed LDR image, achieving impressive results under static camera and scene conditions. However, in real world conditions, ghost-like artifacts and noise effects limit the quality of HDR reconstruction. We address these limitations by introducing a post-acquisition snapshot HDR enhancement scheme that generates a bracketed sequence from a small set of LDR images, and in the extreme case, directly from a single exposure. We achieve this goal via a sparse-based approach where transformations between differently exposed images are encoded through a dictionary learning process, while we learn appropriate features by employing a stacked sparse autoencoder (SSAE) based framework. Via experiments with real images, we demonstrate the improved performance of our method over the state-of-the-art, while our single-shot based HDR formulation provides a novel paradigm for the enhancement of LDR imaging and video sequences.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2019.2933333