Learned image compression with mixed transformer-cnn architectures
Learned image compression (LIC) methods have exhibited promising progress and superior
rate-distortion performance compared with classical image compression standards. Most …
rate-distortion performance compared with classical image compression standards. Most …
Neural video compression with diverse contexts
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 …
encoded can find the relevant contexts from the previous reconstructed signals. Traditional …
Evc: Towards real-time neural image compression with mask decay
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 …
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
Recently, numerous end-to-end optimized image compression neural networks have been
developed and proved themselves as leaders in rate-distortion performance. The main …
developed and proved themselves as leaders in rate-distortion performance. The main …
Mlic: Multi-reference entropy model for learned image compression
Recently, learned image compression has achieved remarkable performance. The entropy
model, which estimates the distribution of the latent representation, plays a crucial role in …
model, which estimates the distribution of the latent representation, plays a crucial role in …
Image coding for machines with omnipotent feature learning
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 …
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 …
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
Recently deep learning-based image compression methods have achieved significant
achievements and gradually outperformed traditional approaches including the latest …
achievements and gradually outperformed traditional approaches including the latest …
Seit: Storage-efficient vision training with tokens using 1% of pixel storage
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 …
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
Semantic communications have shown promising advancements by optimizing source and
channel coding jointly. However, the dynamics of these systems remain understudied …
channel coding jointly. However, the dynamics of these systems remain understudied …