A Microfacet-Based Reflectance Model for Photometric Stereo with Highly Specular Surfaces

Chen, Lixiong; Zheng, Yinqiang; Shi, Boxin; Subpa-asa, Art; Sato, Iwao

doi:10.1109/iccv.2017.343

Cited by 19 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In many applications, e.g. autonomous navigation, augmented reality or robotics, a core computer vision task is to make robust estimates of the surrounding geometry and motion of the device, based on image data [50,11,47,48,38] or other sensor data [23,40,3,22]. Given that these tasks often need to be performed fast, based on unreliable data containing mismatches, and on devices with limited processing power, effi-cient implementations of robust estimation schemes such as RANSAC is paramount.…”

Section: Introductionmentioning

confidence: 99%

Beyond Grobner Bases: Basis Selection for Minimal Solvers

Larsson

Oskarsson

Åström

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Many computer vision applications require robust estimation of the underlying geometry, in terms of camera motion and 3D structure of the scene. These robust methods often rely on running minimal solvers in a RANSAC framework. In this paper we show how we can make polynomial solvers based on the action matrix method faster, by careful selection of the monomial bases. These monomial bases have traditionally been based on a Gröbner basis for the polynomial ideal. Here we describe how we can enumerate all such bases in an efficient way. We also show that going beyond Gröbner bases leads to more efficient solvers in many cases. We present a novel basis sampling scheme that we evaluate on a number of problems.

show abstract

Section: Introductionmentioning

confidence: 99%

Beyond Grobner Bases: Basis Selection for Minimal Solvers

Larsson

Oskarsson

Åström

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…2) Analytic and Empirical Reflectance Model Methods: To handle the non-Lambertian, using analytic or empirical reflectance model to approximate the non-Lambertian BRDFs is a fairly straightforward idea. Along this direction, many models were proposed to fit the nonlinear analytic BRDF, such as the specular spike model [24], the Blinn-Phong model [25], the Torrance-Sparrow model [26], the Ward model and its variations [27], [28], and the microfacet BRDF model [29]. In addition, empirical reflectance models consider the general properties of a BRDF, such as isotropy and monotonicity, to deal with multiple types of surface materials.…”

Section: B Non-lambertian Photometric Stereomentioning

confidence: 99%

Incorporating Lambertian Priors into Surface Normals Measurement

Ju,

Jian,

Guo

et al. 2021

Preprint

View full text Add to dashboard Cite

The goal of photometric stereo is to measure the precise surface normal of a 3D object from observations with various shading cues. However, non-Lambertian surfaces influence the measurement accuracy due to irregular shading cues. Despite deep neural networks have been employed to simulate the performance of non-Lambertian surfaces, the error in specularities, shadows, and crinkle regions is hard to be reduced. In order to address this challenge, we here propose a photometric stereo network that incorporates Lambertian priors to better measure the surface normal. In this paper, we use the initial normal under the Lambertian assumption as the prior information to refine the normal measurement, instead of solely applying the observed shading cues to deriving the surface normal. Our method utilizes the Lambertian information to reparameterize the network weights and the powerful fitting ability of deep neural networks to correct these errors caused by general reflectance properties. Our explorations include: the Lambertian priors (1) reduce the learning hypothesis space, making our method learn the mapping in the same surface normal space and improving the accuracy of learning, and(2) provides the differential features learning, improving the surfaces reconstruction of details. Extensive experiments verify the effectiveness of the proposed Lambertian prior photometric stereo network in accurate surface normal measurement, on the challenging benchmark dataset.

show abstract

“…Besides, the "cow", "pot2" and "reading" results demonstrate that our approach also strongly depends upon the Lambertian assumption: the specular highlights in the images get propagated into the estimated depth. A natural future extension of our method would thus be to cope with such non-Lambertian effects, either by resorting to robust estimation techniques [42], or by adapting our approach to a non-Lambertian image formation model [92].…”

Section: C4 Comparison Against the State-of-the-art On A Public Realmentioning

confidence: 99%

Photometric Depth Super-Resolution

Haefner

Peng

Verma

et al. 2020

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

This study explores the use of photometric techniques (shape-from-shading and uncalibrated photometric stereo) for upsampling the low-resolution depth map from an RGB-D sensor to the higher resolution of the companion RGB image. A single-shot variational approach is first put forward, which is effective as long as the target's reflectance is piecewise-constant. It is then shown that this dependency upon a specific reflectance model can be relaxed by focusing on a specific class of objects (e.g., faces), and delegate reflectance estimation to a deep neural network. A multi-shot strategy based on randomly varying lighting conditions is eventually discussed. It requires no training or prior on the reflectance, yet this comes at the price of a dedicated acquisition setup. Both quantitative and qualitative evaluations illustrate the effectiveness of the proposed methods on synthetic and real-world scenarios.

show abstract

A Microfacet-Based Reflectance Model for Photometric Stereo with Highly Specular Surfaces

Cited by 19 publications

References 33 publications

Beyond Grobner Bases: Basis Selection for Minimal Solvers

Beyond Grobner Bases: Basis Selection for Minimal Solvers

Incorporating Lambertian Priors into Surface Normals Measurement

Photometric Depth Super-Resolution

Contact Info

Product

Resources

About