Unsupervised Continuous Object Representation Networks for Novel View Synthesis

07/30/2020
by   Nicolai Häni, et al.
6

Novel View Synthesis (NVS) is concerned with the generation of novel views of a scene from one or more source images. NVS requires explicit reasoning about 3D object structure and unseen parts of the scene. As a result, current approaches rely on supervised training with either 3D models or multiple target images. We present Unsupervised Continuous Object Representation Networks (UniCORN), which encode the geometry and appearance of a 3D scene using a neural 3D representation. Our model is trained with only two source images per object, requiring no ground truth 3D models or target view supervision. Despite being unsupervised, UniCORN achieves comparable results to the state-of-the-art on challenging tasks, including novel view synthesis and single-view 3D reconstruction.

READ FULL TEXT

page 7

page 8

page 14

page 15

page 16

research
07/12/2021

Fast and Explicit Neural View Synthesis

We study the problem of novel view synthesis of a scene comprised of 3D ...
research
06/04/2019

Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations

The advent of deep learning has given rise to neural scene representatio...
research
04/15/2021

GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds

We present GANcraft, an unsupervised neural rendering framework for gene...
research
03/23/2020

Pix2Shape – Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation

We infer and generate three-dimensional (3D) scene information from a si...
research
07/13/2020

AUTO3D: Novel view synthesis through unsupervisely learned variational viewpoint and global 3D representation

This paper targets on learning-based novel view synthesis from a single ...
research
06/12/2021

A Multi-Implicit Neural Representation for Fonts

Fonts are ubiquitous across documents and come in a variety of styles. T...
research
11/25/2022

Learning 3D Scene Priors with 2D Supervision

Holistic 3D scene understanding entails estimation of both layout config...

Please sign up or login with your details

Forgot password? Click here to reset