all AI news
latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction
March 26, 2024, 4:47 a.m. | Christopher Wewer, Kevin Raj, Eddy Ilg, Bernt Schiele, Jan Eric Lenssen
cs.CV updates on arXiv.org arxiv.org
Abstract: 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 enable fast inference of high resolution novel views due to slow volume rendering, or are limited to interpolation of close input views, even in simpler settings with a single central object, where 360-degree generalization is possible. In this work, we …
3d reconstruction abstract architecture arxiv cs.cv generative inference light novel resolution semantic space type
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US