4 papers
Drop-In Perceptual Optimization for 3D Gaussian Splatting
Ezgi Ozyilkan, Zhiqi Chen, Oren Rippel +2
Despite their output being ultimately consumed by human viewers, 3D Gaussian Splatting (3DGS) methods often rely on ad-hoc combinations of pixel-level losses, resulting in blurry r…
SoftBinary Coding: A New Information-Theoretic Neural Compression Paradigm
Ezgi Ozyilkan, Sharang M. Sriramu, Elza Erkip +2
Neural compression is currently dominated by Nonlinear Transform Coding (NTC), which maps data to real-valued latents via continuous transforms. Despite its success, NTC suffers fr…
Neural Compress-and-Forward for the Primitive Diamond Relay Channel
Ozan Aygün, Ezgi Ozyilkan, Elza Erkip
The diamond relay channel, where a source communicates with a destination via two parallel relays, is one of the canonical models for cooperative communications. We focus on the pr…
Learning-Based Compress-and-Forward Schemes for the Relay Channel
Ezgi Ozyilkan, Fabrizio Carpi, Siddharth Garg +1
The relay channel, consisting of a source-destination pair along with a relay, is a fundamental component of cooperative communications. While the capacity of a general relay chann…