Binocular Photometric Stereo

Du, Hao; Goldman, Dan B; Seitz, Steven M.

doi:10.5244/c.25.84

Cited by 11 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Avenues for future work includes recovering more accurate orientation priors, possibly via semantic analysis [2] or revisiting binocular photometric stereo [13]. Combining orientation priors with depth priors, obtained either from coarse resolution or via commodity depth sensors, is also worth exploring.…”

Section: Resultsmentioning

confidence: 99%

“…So far we have considered using disparity surfaces as orientation priors. We now focus on the case where we are given a surface normal map as prior, obtained for instance via photometric stereo [13] or from Manhattan-world priors [32]. Such normal maps can be used in our SGM-P algorithm, though the situation is more complex than one might expect.…”

Section: Surface Normal Priorsmentioning

confidence: 99%

See 1 more Smart Citation

Semi-global Stereo Matching with Surface Orientation Priors

Scharstein

Taniai

Sinha

2017

2017 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

Semi-Global Matching (SGM) is a widely-used efficient stereo matching technique. It works well for textured scenes, but fails on untextured slanted surfaces due to its fronto-parallel smoothness assumption. To remedy this problem, we propose a simple extension, termed SGM-P, to utilize precomputed surface orientation priors. Such priors favor different surface slants in different 2D image regions or 3D scene regions and can be derived in various ways. In this paper we evaluate plane orientation priors derived from stereo matching at a coarser resolution and show that such priors can yield significant performance gains for difficult weakly-textured scenes. We also explore surface normal priors derived from Manhattan-world assumptions, and we analyze the potential performance gains using oracle priors derived from ground-truth data. SGM-P only adds a minor computational overhead to SGM and is an attractive alternative to more complex methods employing higher-order smoothness terms.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Surface Normal Priorsmentioning

confidence: 99%

Semi-global Stereo Matching with Surface Orientation Priors

Scharstein

Taniai

Sinha

2017

2017 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

show abstract

“…Thus, PS is often used to enhance the detail of low-resolution geometry obtained independently with MVS [11,27]. The benefits of simultaneous computation of MVS and PS are investigated in [8], but only for static objects. To make the problem convex, their method approximates depth as a piecewise linear function.…”

Section: Related Workmentioning

confidence: 99%

“…2(a). We define triplets of RGB sources T t (e.g., T t ∈ { [5,6,1], [2,9,4], [8,3,7]}) that are turned on one at a time in a sequential manner, each for the duration of one video frame (please see supplementary video). These RGB triplets can be defined in different ways.…”

Section: Pgsf With 9 Colored Lightsmentioning

confidence: 99%

Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction

Gotardo

Simon

Sheikh

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Photometric stereo (PS) is an established technique for high-detail reconstruction of 3D geometry and appearance. To correct for surface integration errors, PS is often combined with multiview stereo (MVS). With dynamic objects, PS reconstruction also faces the problem of computing optical flow (OF) for image alignment under rapid changes in illumination. Current PS methods typically compute optical flow and MVS as independent stages, each one with its own limitations and errors introduced by early regularization. In contrast, scene flow methods estimate geometry and motion, but lack the fine detail from PS. This paper proposes photogeometric scene flow (PGSF) for high-quality dynamic 3D reconstruction. PGSF performs PS, OF, and MVS simulta-neously. It is based on two key observations: (i) while image alignment improves PS, PS allows for surfaces to be relit to improve alignment; (ii) PS provides surface gradients that render the smoothness term in MVS unnecessary, leading to truly data-driven, continuous depth estimates. This synergy is demonstrated in the quality of the resulting RGB appearance, 3D geometry, and 3D motion.

show abstract

“…This work differs from classical photometric stereo approaches as the final reconstruction is the fusion of different shape from shading reconstructions, each obtained independently from a single image. Other approaches use the perspective projection in hybrid reconstruction algorithms to fuse photometric cues with active stereo [21,34] or passive stereo [10,19].…”

Section: Prior Workmentioning

confidence: 99%

A New Perspective on Uncalibrated Photometric Stereo

Papadhimitri

Favaro

2013

2013 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

We investigate the problem of reconstructing normals, albedo and lights of Lambertian surfaces in uncalibrated photometric stereo under the perspective projection model. Our analysis is based on establishing the integrability constraint. In the orthographic projection case, it is well-known that when such constraint is imposed, a solution can be identified only up to 3 parameters, the so-called generalized bas-relief (GBR) ambiguity. We show that in the perspective projection case the solution is unique. We also propose a closed-form solution which is simple, efficient and robust. We test our algorithm on synthetic data and publicly available real data. Our quantitative tests show that our method outperforms all prior work of uncalibrated photometric stereo under orthographic projection.

show abstract

Binocular Photometric Stereo

Cited by 11 publications

References 23 publications

Semi-global Stereo Matching with Surface Orientation Priors

Semi-global Stereo Matching with Surface Orientation Priors

Photogeometric Scene Flow for High-Detail Dynamic 3D Reconstruction

A New Perspective on Uncalibrated Photometric Stereo

Contact Info

Product

Resources

About