latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wewer, Christopher, Raj, Kevin, Ilg, Eddy, Schiele, Bernt, Lenssen, Jan Eric
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910546312298496
author Wewer, Christopher
Raj, Kevin
Ilg, Eddy
Schiele, Bernt
Lenssen, Jan Eric
author_facet Wewer, Christopher
Raj, Kevin
Ilg, Eddy
Schiele, Bernt
Lenssen, Jan Eric
contents We present latentSplat, a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. Existing methods for generalizable 3D reconstruction either do not scale to large scenes and resolutions, or are limited to interpolation of close input views. latentSplat combines the strengths of regression-based and generative approaches while being trained purely on readily available real video data. The core of our method are variational 3D Gaussians, a representation that efficiently encodes varying uncertainty within a latent space consisting of 3D feature Gaussians. From these Gaussians, specific instances can be sampled and rendered via efficient splatting and a fast, generative decoder. We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.
format Preprint
id arxiv_https___arxiv_org_abs_2403_16292
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
Wewer, Christopher
Raj, Kevin
Ilg, Eddy
Schiele, Bernt
Lenssen, Jan Eric
Computer Vision and Pattern Recognition
We present latentSplat, a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. Existing methods for generalizable 3D reconstruction either do not scale to large scenes and resolutions, or are limited to interpolation of close input views. latentSplat combines the strengths of regression-based and generative approaches while being trained purely on readily available real video data. The core of our method are variational 3D Gaussians, a representation that efficiently encodes varying uncertainty within a latent space consisting of 3D feature Gaussians. From these Gaussians, specific instances can be sampled and rendered via efficient splatting and a fast, generative decoder. We show that latentSplat outperforms previous works in reconstruction quality and generalization, while being fast and scalable to high-resolution data.
title latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.16292