CAESR: Conditional Autoencoder and Super-Resolution for Learned Spatial Scalability

In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Visual communications and image processing (Online) s. 1 - 5
Hlavní autoři: Bonnineau, Charles, Hamidouche, Wassim, Travers, Jean-Francois, Sidaty, Naty, Aubie, Jean-Yves, Deforges, Olivier
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 05.12.2021
Témata:
Conditional Autoencoder
Encoding
Image coding
Scalability
Spatial Scalability
Super-Resolution
Superresolution
Training
Video coding
Visual communication
VVC
ISSN:2642-9357
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:In this paper, we present CAESR, an hybrid learning-based coding approach for spatial scalability based on the versatile video coding (VVC) standard. Our framework considers a low-resolution signal encoded with VVC intra-mode as a base-layer (BL), and a deep conditional autoencoder with hyperprior (AE-HP) as an enhancement-layer (EL) model. The EL encoder takes as inputs both the upscaled BL reconstruction and the original image. Our approach relies on conditional coding that learns the optimal mixture of the source and the upscaled BL image, enabling better performance than residual coding. On the decoder side, a super-resolution (SR) module is used to recover high-resolution details and invert the conditional coding process. Experimental results have shown that our solution is competitive with the VVC full-resolution intra coding while being scalable.
ISSN:2642-9357
DOI:10.1109/VCIP53242.2021.9675351