Jun 14, 2024 · We consider the Distributed Source Coding (DSC) problem concerning the task of encoding an input in the absence of correlated side information that is only available to the decoder.

Jun 5, 2021 · We evaluate our method on multiple datasets and show that our method can handle complex correlations and achieves state-of-the-art PSNR. Our code is made available at this https URL.

Rather than relying on hand-crafted source-modeling, our method utilizes a powerful conditional deep generative model to learn the distributed encoder and decoder. We evaluate our method on realistic …

Jun 5, 2021 · Rather than relying on hand-crafted source-modeling, our method utilizes a powerful conditional deep generative model to learn the distributed encoder and decoder. We evaluate our …

Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational Autoencoder (VQ-VAE) to learn the distributed encoder and decoder.

In this work, we propose a novel distributed compression framework composed of independent encoders and a joint decoder, which we call neural distributed principal component analysis (NDPCA).

Oct 23, 2024 · We consider the Distributed Source Coding (DSC) problem concerning the task of encoding an input in the absence of correlated side information that is only available to the decoder.

Rather than relying on hand-crafted source modeling, our method utilizes a conditional Vector-Quantized Variational AutoEncoder (VQ-VAE) to learn the distributed encoder and decoder.

Aug 20, 2023 · Distributed source coding (DSC) refers to the task of compressing multiple correlated data sources that are encoded separately but decoded jointly. A canonical example is a pair of …

We introduce Neural DSC, a compression scheme for lossy distributed source coding based on a particular type of VAE (VQ-VAE). The VQ-VAE architecture contains a codebook learned during …