Weakly supervised learning of multi-object 3D scene decompositions using deep shape priors-Reference-Cited by-同舟云学术

Weakly supervised learning of multi-object 3D scene decompositions using deep shape priors

Published:2022-07 Issue: Volume:220 Page:103440
ISSN:1077-3142
Container-title:Computer Vision and Image Understanding
language:en
Short-container-title:Computer Vision and Image Understanding

Author:

Elich Cathrin^ORCID,Oswald Martin R.,Pollefeys Marc,Stueckler Joerg^ORCID

Publisher

Elsevier BV

Subject

Computer Vision and Pattern Recognition,Signal Processing,Software

Reference74 articles.

1. Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L., 2018. Learning Representations and Generative Models for 3D Point Clouds. In: Proc. of the International Conference on Machine Learning. ICML.

2. Athalye, A., Engstrom, L., Ilyas, A., Kwok, K., 2018. Synthesizing Robust Adversarial Examples. In: Int. Conf. on Machine Learning. ICML.

3. MONet: Unsupervised scene decomposition and representation;Burgess,2019

4. ShapeNet: An information-rich 3D model repository;Chang,2015

5. ROOTS: Object-centric representation and rendering of 3D scenes;Chen;J. Mach. Learn. Res.,2021

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. A new deep CNN for 3D text localization in the wild through shadow removal;Computer Vision and Image Understanding;2024-01

2. Disentangling Visual Priors: Unsupervised Learning of Scene Interpretations with Compositional Autoencoder;Lecture Notes in Computer Science;2024

3. Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning;2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR);2023-06