AICT: An Adaptive Image Compression Transformer - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

AICT: An Adaptive Image Compression Transformer

Résumé

Motivated by the efficiency investigation of the Tranformer-based transform coding framework, namely SwinT-ChARM, we propose to enhance the latter, as first, with a more straightforward yet effective Tranformer-based channel-wise auto-regressive prior model, resulting in an absolute image compression transformer (ICT). Current methods that still rely on ConvNet-based entropy coding are limited in long-range modeling dependencies due to their local connectivity and an increasing number of architectural biases and priors. On the contrary, the proposed ICT can capture both global and local contexts from the latent representations and better parameterize the distribution of the quantized latents. Further, we leverage a learnable scaling module with a sandwich ConvNeXt-based pre/post-processor to accurately extract more compact latent representation while reconstructing higher-quality images. Extensive experimental results on benchmark datasets showed that the proposed adaptive image compression transformer (AICT) framework significantly improves the trade-off between coding efficiency and decoder complexity over the versatile video coding (VVC) reference encoder (VTM-18.0) and the neural codec SwinT-ChARM.

Dates et versions

hal-04356642 , version 1 (20-12-2023)

Identifiants

Citer

Ahmed Ghorbel, Wassim Hamidouche, Luce Morin. AICT: An Adaptive Image Compression Transformer. 2023 IEEE International Conference on Image Processing (ICIP), Oct 2023, Kuala Lumpur, Malaysia. ⟨10.1109/icip49359.2023.10222799⟩. ⟨hal-04356642⟩
11 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More