Unsupervised Discovery of Object Radiance Fields

2021-07-16 · ICLR 2022 4 · Hong-Xing Yu, Leonidas J. Guibas, Jiajun Wu

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 enables novel tasks, such as scene segmentation and editing in 3D, and it performs well on these tasks and on novel view synthesis on three datasets.

📄 PDF Abstract BibTeX arXiv:2107.07905

Code (1)

KovenYu/uORF 공식 구현 pytorch

Tasks

Novel View SynthesisObjectScene Segmentation

Methods 이 논문이 사용한 방법론

Robinhood Customer Care Number +1-833-534-1729 설명 없음

Unsupervised Discovery and Composition of Object Light Fields

2022-05-08 · Cameron Smith, Hong-Xing Yu, Sergey Zakharov, Fredo Durand 외

Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding. Recent efforts have tackled unsupervised discovery of object-centric neural scene r…

Novel View Synthesis Object Scene Understanding

Slot-guided Volumetric Object Radiance Fields

2024-01-04 · NeurIPS 2023 11 · Di Qi, Tong Yang, Xiangyu Zhang

We present a novel framework for 3D object-centric representation learning. Our approach effectively decomposes complex scenes into individual objects from a single image in an unsupervised fashion. This method, called s…

Object Representation Learning

Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects

2022-09-09 · Ziyu Wang, Yu Deng, Jiaolong Yang, Jingyi Yu 외

3D-aware generative models have demonstrated their superb performance to generate 3D neural radiance fields (NeRF) from a collection of monocular 2D images even for topology-varying object categories. However, these meth…

Disentanglement Image Generation NeRF Object

Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation

2022-01-01 · CVPR 2022 1 · Shengqu Cai, Anton Obukhov, Dengxin Dai, Luc van Gool

We propose a pipeline to generate Neural Radiance Fields (NeRF) of an object or a scene of a specific class, conditioned on a single input image. This is a challenging task, as training NeRF requires multiple views o…

3D-Aware Image Synthesis Image Generation NeRF Novel View Synthesis+2

Pix2NeRF: Unsupervised Conditional $π$-GAN for Single Image to Neural Radiance Fields Translation

2022-02-26 · Shengqu Cai, Anton Obukhov, Dengxin Dai, Luc van Gool

We propose a pipeline to generate Neural Radiance Fields~(NeRF) of an object or a scene of a specific class, conditioned on a single input image. This is a challenging task, as training NeRF requires multiple views of th…