Learned image compression (LIC) methods have exhibited promising progress and superior
rate-distortion performance compared with classical image compression standards. Most …

Abstract 3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel
view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial …

We show how transformers can be used to vastly simplify neural video compression.
Previous methods have been relying on an increasing number of architectural biases and …

By optimizing the rate-distortion-realism trade-off, generative compression approaches
produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions …

This paper outlines an end-to-end optimized lossy image compression framework using
diffusion generative models. The approach relies on the transform coding paradigm, where …

Implicit neural representations (INRs) recently achieved great success in image
representation and compression, offering high visual quality and fast rendering speeds with …

Many common types of data can be represented as functions that map coordinates to signal
values, such as pixel locations to RGB values in the case of an image. Based on this view …

Most neural compression models are trained on large datasets of images or videos in order
to generalize to unseen data. Such generalization typically requires large and expressive …

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 …

Image codecs are typically optimized to trade-off bitrate vs. distortion metrics. At low bitrates,
this leads to compression artefacts which are easily perceptible, even when training with …