SinGRAF: Learning a 3D Generative Radiance Field for a Single Scene

11/30/2022
by   Minjung Son, et al.
0

Generative models have shown great promise in synthesizing photorealistic 3D objects, but they require large amounts of training data. We introduce SinGRAF, a 3D-aware generative model that is trained with a few input images of a single scene. Once trained, SinGRAF generates different realizations of this 3D scene that preserve the appearance of the input while varying scene layout. For this purpose, we build on recent progress in 3D GAN architectures and introduce a novel progressive-scale patch discrimination approach during training. With several experiments, we demonstrate that the results produced by SinGRAF outperform the closest related works in both quality and diversity by a large margin.

READ FULL TEXT

page 1

page 5

page 6

page 7

page 12

page 13

page 14

page 15

research
03/24/2021

One-Shot GAN: Learning to Generate Samples from Single Images and Videos

Given a large number of training samples, GANs can achieve remarkable pe...
research
11/27/2022

3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene

We introduce 3inGAN, an unconditional 3D generative model trained from 2...
research
04/25/2023

Patch-based 3D Natural Scene Generation from a Single Example

We target a 3D generative model for general natural scenes that are typi...
research
12/10/2020

Full-Glow: Fully conditional Glow for more realistic image generation

Autonomous agents, such as driverless cars, require large amounts of lab...
research
01/31/2023

LM-GAN: A Photorealistic All-Weather Parametric Sky Model

We present LM-GAN, an HDR sky model that generates photorealistic enviro...
research
05/12/2021

Learning to Generate Novel Scene Compositions from Single Images and Videos

Training GANs in low-data regimes remains a challenge, as overfitting of...
research
03/23/2023

Persistent Nature: A Generative Model of Unbounded 3D Worlds

Despite increasingly realistic image quality, recent 3D image generative...

Please sign up or login with your details

Forgot password? Click here to reset