Learned image compression with mixed transformer-cnn architectures

J Liu, H Sun, J Katto - … of the IEEE/CVF conference on …, 2023 - openaccess.thecvf.com
Learned image compression (LIC) methods have exhibited promising progress and superior
rate-distortion performance compared with classical image compression standards. Most …

Neural video compression with diverse contexts

J Li, B Li, Y Lu - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
For any video codecs, the coding efficiency highly relies on whether the current signal to be
encoded can find the relevant contexts from the previous reconstructed signals. Traditional …

Evc: Towards real-time neural image compression with mask decay

GH Wang, J Li, B Li, Y Lu - arxiv preprint arxiv:2302.05071, 2023 - arxiv.org
Neural image compression has surpassed state-of-the-art traditional codecs (H. 266/VVC)
for rate-distortion (RD) performance, but suffers from large complexity and separate models …

Lvqac: Lattice vector quantization coupled with spatially adaptive companding for efficient learned image compression

X Zhang, X Wu - Proceedings of the IEEE/CVF Conference …, 2023 - openaccess.thecvf.com
Recently, numerous end-to-end optimized image compression neural networks have been
developed and proved themselves as leaders in rate-distortion performance. The main …

Mlic: Multi-reference entropy model for learned image compression

W Jiang, J Yang, Y Zhai, P Ning, F Gao… - Proceedings of the 31st …, 2023 - dl.acm.org
Recently, learned image compression has achieved remarkable performance. The entropy
model, which estimates the distribution of the latent representation, plays a crucial role in …

Image coding for machines with omnipotent feature learning

R Feng, X **, Z Guo, R Feng, Y Gao, T He… - … on Computer Vision, 2022 - Springer
Abstract Image Coding for Machines (ICM) aims to compress images for AI tasks analysis
rather than meeting human perception. Learning a kind of feature that is both general (for AI …

Efficient hierarchical entropy model for learned point cloud compression

R Song, C Fu, S Liu, G Li - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Learning an accurate entropy model is a fundamental way to remove the redundancy in
point cloud compression. Recently, the octree-based auto-regressive entropy model which …

Learned image compression with gaussian-laplacian-logistic mixture model and concatenated residual modules

H Fu, F Liang, J Lin, B Li, M Akbari… - … on Image Processing, 2023 - ieeexplore.ieee.org
Recently deep learning-based image compression methods have achieved significant
achievements and gradually outperformed traditional approaches including the latest …

Seit: Storage-efficient vision training with tokens using 1% of pixel storage

S Park, S Chun, B Heo, W Kim… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We need billion-scale images to achieve more generalizable and ground-breaking vision
models, as well as massive dataset storage to ship the images (eg, the LAION-4B dataset …

On the role of ViT and CNN in semantic communications: Analysis and prototype validation

H Yoo, L Dai, S Kim, CB Chae - IEEE Access, 2023 - ieeexplore.ieee.org
Semantic communications have shown promising advancements by optimizing source and
channel coding jointly. However, the dynamics of these systems remain understudied …