We consider the task of generating realistic 3D shapes, which is useful for a variety of
applications such as automatic scene generation and physical simulation. Compared to …

Neural radiance-density field methods have become increasingly popular for the task of
novel-view rendering. Their recent extension to hash-based positional encoding ensures …

This paper introduces a new parameterization of deep neural networks (both fully-connected
and convolutional) with guaranteed $\ell^ 2$ Lipschitz bounds, ie limited sensitivity to input …

Offline reinforcement learning (RL) methods can generally be categorized into two types: RL-
based and Imitation-based. RL-based methods could in principle enjoy out-of-distribution …

As recent advances in Neural Radiance Fields (NeRF) have enabled high-fidelity 3D face
reconstruction and novel view synthesis, its manipulation also became an essential task in …

Rehearsal approaches enjoy immense popularity with Continual Learning (CL)
practitioners. These methods collect samples from previously encountered data distributions …

Recent work on radiance fields and volumetric inverse rendering (eg, NeRFs) has provided
excellent results in building data-driven models of real scenes for novel view synthesis with …

The long runtime of high-fidelity partial differential equation (PDE) solvers makes them
unsuitable for time-critical applications. We propose to accelerate PDE solvers using …

Recently, the image-wise implicit neural representation of videos, NeRV, has gained
popularity for its promising results and swift speed compared to regular pixel-wise implicit …

3D Gaussian Splatting (3DGS) is a promising technique for 3D reconstruction, offering
efficient training and rendering speeds, making it suitable for real-time applications …