Unsupervised Discovery of Object Radiance Fields

07/16/2021
by   Hong-Xing Yu, et al.
1

We study the problem of inferring an object-centric scene representation from a single image, aiming to derive a representation that explains the image formation process, captures the scene's 3D nature, and is learned without supervision. Most existing methods on scene decomposition lack one or more of these characteristics, due to the fundamental challenge in integrating the complex 3D-to-2D image formation process into powerful inference schemes like deep networks. In this paper, we propose unsupervised discovery of Object Radiance Fields (uORF), integrating recent progresses in neural 3D scene representations and rendering with deep inference networks for unsupervised 3D scene decomposition. Trained on multi-view RGB images without annotations, uORF learns to decompose complex scenes with diverse, textured background from a single image. We show that uORF performs well on unsupervised 3D scene segmentation, novel view synthesis, and scene editing on three datasets.

READ FULL TEXT

page 2

page 3

page 6

page 8

page 9

research
05/08/2022

Unsupervised Discovery and Composition of Object Light Fields

Neural scene representations, both continuous and discrete, have recentl...
research
10/14/2022

Novel 3D Scene Understanding Applications From Recurrence in a Single Image

We demonstrate the utility of recurring pattern discovery from a single ...
research
10/07/2021

Unsupervised Image Decomposition with Phase-Correlation Networks

The ability to decompose scenes into their object components is a desire...
research
07/22/2022

Seeing 3D Objects in a Single Image via Self-Supervised Static-Dynamic Disentanglement

Human perception reliably identifies movable and immovable parts of 3D s...
research
10/02/2022

Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation

We present radiance field propagation (RFP), a novel approach to segment...
research
11/22/2022

ONeRF: Unsupervised 3D Object Segmentation from Multiple Views

We present ONeRF, a method that automatically segments and reconstructs ...
research
11/25/2020

DeRF: Decomposed Radiance Fields

With the advent of Neural Radiance Fields (NeRF), neural networks can no...

Please sign up or login with your details

Forgot password? Click here to reset