RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images

Y Peng, A Ganesh, J Wright, W Xu… - IEEE transactions on …, 2012 - ieeexplore.ieee.org
This paper studies the problem of simultaneously aligning a batch of linearly correlated
images despite gross corruption (such as occlusion). Our method seeks an optimal set of …

Non-convex robust PCA

P Netrapalli, N UN, S Sanghavi… - Advances in neural …, 2014 - proceedings.neurips.cc
We propose a new provable method for robust PCA, where the task is to recover a low-rank
matrix, which is corrupted with sparse perturbations. Our method consists of simple …

TILT: Transform invariant low-rank textures

Z Zhang, A Ganesh, X Liang, Y Ma - International journal of computer …, 2012 - Springer
In this paper, we propose a new tool to efficiently extract a class of “low-rank textures” in a
3D scene from user-specified windows in 2D images despite significant corruptions and …

[PDF][PDF] 从压缩传感到低秩矩阵恢复: 理论与应用

彭义刚, 索津莉, 戴琼海, 徐文立 - 自动化学报, 2013 - aas.net.cn
摘要综述了压缩传感, 矩阵秩最小化和低秩矩阵恢复等方面的基础理论及典型应用.
基于凸优化的压缩传感及由其衍生的矩阵秩最小化和低秩矩阵恢复是近年来的研究热点 …

From compressed sensing to low-rank matrix recovery: theory and applications

P Yi-Gang, S Jin-Li, DAI Qiong-Hai, XU Wen-Li - Acta Automatica Sinica, 2013 - Elsevier
This paper reviews the basic theory and typical applications of compressed sensing, matrix
rank minimization, and low-rank matrix recovery. Compressed sensing based on convex …

Reweighted low-rank matrix recovery and its application in image restoration

Y Peng, J Suo, Q Dai, W Xu - IEEE transactions on cybernetics, 2014 - ieeexplore.ieee.org
In this paper, we propose a reweighted low-rank matrix recovery method and demonstrate
its application for robust image restoration. In the literature, principal component pursuit …

Accelerated alternating projections for robust principal component analysis

HQ Cai, JF Cai, K Wei - Journal of Machine Learning Research, 2019 - jmlr.org
We study robust PCA for the fully observed setting, which is about separating a low rank
matrix L and a sparse matrix S from their sum D= L+ S. In this paper, a new algorithm …

Linearized alternating direction method with adaptive penalty and warm starts for fast solving transform invariant low-rank textures

X Ren, Z Lin - International journal of computer vision, 2013 - Springer
Transform invariant low-rank textures (TILT) is a novel and powerful tool that can effectively
rectify a rich class of low-rank textures in 3D scenes from 2D images despite significant …

Single-view 3D scene reconstruction and parsing by attribute grammar

X Liu, Y Zhao, SC Zhu - IEEE transactions on pattern analysis …, 2017 - ieeexplore.ieee.org
In this paper, we present an attribute grammar for solving two coupled tasks: i) parsing a 2D
image into semantic regions; and ii) recovering the 3D scene structures of all regions. The …

Single-view 3d scene parsing by attributed grammar

X Liu, Y Zhao, SC Zhu - Proceedings of the IEEE …, 2014 - openaccess.thecvf.com
In this paper, we present an attributed grammar for parsing man-made outdoor scenes into
semantic surfaces, and recovering its 3D model simultaneously. The grammar takes …