← Search

Rajhans Singh

2 accepted papers

2023

Polynomial Implicit Neural Representations for Large Diverse Datasets

CVPR 2023highlight

Implicit neural representations (INR) have gained significant popularity for signal and image representation for many end-tasks, such as superresolution, 3D modeling, and more. Most INR architectures rely on sinusoidal positional encoding, which accounts for high-frequency information in data. Howev…

2019

Non-Parametric Priors For Generative Adversarial Networks

ICML 2019oral

The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging. However, one of the common assumptions in most GAN architectures is the assumption of simple parametric latent-space distributio…

Cited by 17SourcePDFScholar