Tensors, or multidimensional arrays, are data structures that can naturally represent visual
data of multiple dimensions. Inherently able to efficiently capture structured, latent semantic …

Most existing geometry processing algorithms use meshes as the default shape
representation. Manipulating meshes, however, requires one to maintain high quality in the …

Neural fields have emerged as a new paradigm for representing signals, thanks to their
ability to do it compactly while being easy to optimize. In most applications, however, neural …

Deep learning has catalysed progress in tasks such as face recognition and analysis,
leading to a quick integration of technological solutions in multiple layers of our society …

Despite the remarkable capabilities of deep neural networks in image recognition, the
dependence on activation functions remains a largely unexplored area and has yet to be …

This paper addresses the problem of finding interpretable directions in the latent space of
pre-trained Generative Adversarial Networks (GANs) to facilitate controllable image …

Deep neural networks have been the driving force behind the success in classification tasks,
eg, object and audio recognition. Impressive results and generalization have been achieved …

Generative modeling has evolved to a notable field of machine learning. Deep polynomial
neural networks (PNNs) have demonstrated impressive results in unsupervised image …

Abstract We introduce MIGS (Multi-Identity Gaussian Splatting), a novel method that learns a
single neural representation for multiple identities, using only monocular videos. Recent 3D …

The Mixture of Experts (MoE) paradigm provides a powerful way to decompose inscrutable
dense layers into smaller, modular computations often more amenable to human …