Complexity Scalable Learning-Based Image Decoding

Recently, learning-based image compression has attracted a lot of attention, leading to the development of a new JPEG AI standard based on neural networks. Typically, this type of coding solution has much lower encoding complexity compared to conventional coding standards such as HEVC and VVC (Intra...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2023 IEEE International Conference on Image Processing (ICIP) s. 1860 - 1864
Hlavní autoři: Munna, Tahsir Ahmed, Ascenso, Joao
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 08.10.2023
Témata:
complexity scalability
Costs
hyperprior
Image coding
learning-based image compression
Mobile handsets
Neural networks
Rate-distortion
Training
Transform coding
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Recently, learning-based image compression has attracted a lot of attention, leading to the development of a new JPEG AI standard based on neural networks. Typically, this type of coding solution has much lower encoding complexity compared to conventional coding standards such as HEVC and VVC (Intra mode) but has much higher decoding complexity. Therefore, to promote the wide adoption of learning-based image compression, especially to resource-constrained (such as mobile) devices, it is important to achieve lower decoding complexity even if at the cost of some coding efficiency. This paper proposes a complexity scalable decoder that can control the decoding complexity by proposing a novel procedure to learn the filters of the convolutional layers at the decoder by varying the number of channels at each layer, effectively having simple to more complex decoding networks. A regularization loss is employed with pruning after training to obtain a set of scalable layers, which may use more or fewer channels depending on the complexity budget. Experimental results show that complexity can be significantly reduced while still allowing a competitive rate-distortion performance.
DOI:10.1109/ICIP49359.2023.10222047