YouTube video by Aalto University

Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting

We present Smol-GS, a novel method for learning compact representations for 3D Gaussian Splatting (3DGS). Our approach learns highly efficient splat-wise features to model 3D space, which capture abst...

Vector quantization is common in deep models, yet its hard assignments block gradients and hinder end-to-end training. We propose DiVeQ, which treats quantization as adding an error vector that mimics...

YouTube video by Aalto University

DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering

Efficiently performing probabilistic inference in large models is a significant challenge due to the high computational demands and continuous nature of the model parameters. At the same time, the...

The Hilbert-space Gaussian Process (HGP) approach offers a hyperparameter-independent basis function approximation for speeding up Gaussian Process (GP) inference by projecting the GP onto M basis fun...