Toward Guaranteed Illumination Models for Non-convex Objects

Zhang, Yuqian; Mu, Cun; Kuo, Han-Wen; Wright, John

doi:10.1109/iccv.2013.120

Cited by 10 publications

(11 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let L Y denote the corresponding label set. If the Y i are sufficiently expressive [18], a new input sample from the i-th class, stacked as a vector y t ∈ R M , will have a sparse representation y t = Yx in terms of the training data Y: x will be nonzero only for those samples from class i. The sparse coefficient vector x ∈ R N can be estimated by solving the following optimization problemx…”

Section: A Sparse Representation-based Classificationmentioning

confidence: 99%

Sparse Representation-Based Open Set Recognition

Zhang

Patel

2017

IEEE Trans. Pattern Anal. Mach. Intell.

182

View full text Add to dashboard Cite

Abstract-We propose a generalized Sparse Representationbased Classification (SRC) algorithm for open set recognition where not all classes presented during testing are known during training. The SRC algorithm uses class reconstruction errors for classification. As most of the discriminative information for open set recognition is hidden in the tail part of the matched and sum of non-matched reconstruction error distributions, we model the tail of those two error distributions using the statistical Extreme Value Theory (EVT). Then we simplify the open set recognition problem into a set of hypothesis testing problems. The confidence scores corresponding to the tail distributions of a novel test sample are then fused to determine its identity. The effectiveness of the proposed method is demonstrated using four publicly available image and object classification datasets and it is shown that this method can perform significantly better than many competitive open set recognition algorithms. Code is public available: https://github.com/hezhangsprinter/SROSR Index Terms-Open set recognition, sparse representationbased classification, extreme value theory.

show abstract

Section: A Sparse Representation-based Classificationmentioning

confidence: 99%

Sparse Representation-Based Open Set Recognition

Zhang

Patel

2017

IEEE Trans. Pattern Anal. Mach. Intell.

182

View full text Add to dashboard Cite

show abstract

“…the small ρ scenarios). be used to remove the shadows and specularities [3,8]. Here, we solved problem (1.4) for YaleB face images [43].…”

Section: Shadow and Specularity Removal From Face Imagesmentioning

confidence: 99%

“…Accordingly, all the above provide theoretical guarantees for CPCP, under fairly mild conditions, to produce accurate estimates of L 0 and P Ω [S 0 ] (or S 0 ), even when the number of measurements p is substantially less than mn. Inspired by these theoretical results, researchers from different fields have leveraged CPCP to solve many practical problems, including video background modeling [3], batch image alignment [7], face verification [8], photometric stereo [9], dynamic MRI [10], topic modeling [11], latent variable graphical model learning [12] and outlier detection and robust Principal Component Analysis [3], to name just a few.…”

mentioning

confidence: 99%

Scalable Robust Matrix Recovery: Frank--Wolfe Meets Proximal Methods

Mu¹,

Zhang²,

Wright³

et al. 2016

SIAM J. Sci. Comput.

Self Cite

View full text Add to dashboard Cite

Recovering matrices from compressive and grossly corrupted observations is a fundamental problem in robust statistics, with rich applications in computer vision and machine learning. In theory, under certain conditions, this problem can be solved in polynomial time via a natural convex relaxation, known as Compressive Principal Component Pursuit (CPCP). However, many existing provably convergent algorithms for CPCP suffer from superlinear per-iteration cost, which severely limits their applicability to large-scale problems. In this paper, we propose provably convergent, scalable and efficient methods to solve CPCP with (essentially) linear per-iteration cost. Our method combines classical ideas from Frank-Wolfe and proximal methods. In each iteration, we mainly exploit Frank-Wolfe to update the low-rank component with rank-one SVD and exploit the proximal step for the sparse term. Convergence results and implementation details are discussed. We demonstrate the practicability and scalability of our approach with numerical experiments on visual data. AMS subject classifications. 90C06, 90C25, 90C52(1.3) minThis convex surrogate is sometimes referred to as compressive principal component pursuit (CPCP) [1]. Equivalently, since). JW was funded by ONR-N00014-13-0492. arXiv:1403.7588v2 [math.OC] 29 May 2017 * To transform problem (1.3) into problem (1.4), simple procedures like Gram-chmidt might be invoked. Despite being equivalent, one formulation might be preferred over the other in practice, depending on the specifications of the sensing operator A[·]. In this paper, we will mainly focus on solving problem (1.4) and its variants. Our methods, however, are not restrictive to (1.4) and can be easily extended to problem (1.3).

show abstract

“…If a Lambertian object is convex, its appearance approximately lies in a nine-dimensional subspace [3,12,11,13], making it impossible to reconstruct more than a 3 × 3 environment map. For non-convex objects, an image of the object under all possible lighting conditions lies in a much higher dimension space due to shadows and occlusions [20], enabling the reconstruction of light beyond 3 × 3 [7]. But in general, matte surfaces are tough to work with.…”

Section: Related Workmentioning

confidence: 99%

SparkleVision: Seeing the world through random specular microfacets

Zhang

Isola

Adelson

2015

2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

In this paper, we study the problem of reproducing the world lighting from a single image of an object covered with random specular microfacets on the surface. We show that such reflectors can be interpreted as a randomized mapping from the lighting to the image. Such specular objects have very different optical properties from both diffuse surfaces and smooth specular objects like metals, so we design special imaging system to robustly and effectively photograph them. We present simple yet reliable algorithms to calibrate the proposed system and do the inference. We conduct experiments to verify the correctness of our model assumptions and prove the effectiveness of our pipeline.

show abstract

Toward Guaranteed Illumination Models for Non-convex Objects

Cited by 10 publications

References 27 publications

Sparse Representation-Based Open Set Recognition

Sparse Representation-Based Open Set Recognition

Scalable Robust Matrix Recovery: Frank--Wolfe Meets Proximal Methods

SparkleVision: Seeing the world through random specular microfacets

Contact Info

Product

Resources

About