TY - CHAP A1 - Ju, Yong Chul A1 - Maurer, Daniel A1 - Breuß, Michael A1 - Bruhn, Andrés ED - Breuß, Michael ED - Bruckstein, Alfred ED - Maragos, Petros ED - Wuhrer, Stefanie T1 - Direct variational perspective shape from shading with Cartesian depth parametrisation T2 - Perspectives in Shape Analysis, Mathematics and Visualization Y1 - 2016 SN - 978-3-319-24724-3 U6 - https://doi.org/10.1007/978-3-319-24726-7 SP - 43 EP - 72 PB - Springer International Publishing CY - Cham ER - TY - CHAP A1 - Kleefeld, Andreas A1 - Ju, Yong Chul A1 - Tozza, Silvia A1 - Breuß, Michael A1 - Bruhn, Andrés ED - Burghardt, Tilo ED - Damen, Dima ED - Mayol-Cuevas, Walterio ED - Mirmehdi, Majid T1 - Generalised Perspective Shape from Shading with Oren-Nayar Reflectance T2 - Proceedings 24th British Machine Vision Conference, BMVC 2013, Bristol, UK, September 2013 N2 - In spite of significant advances in Shape from Shading (SfS) over the last years, it is still a challenging task to design SfS approaches that are flexible enough to handle a wide range of input scenes. In this paper, we address this lack of flexibility by proposing a novel model that extends the range of possible applications. To this end, we consider the class of modern perspective SfS models formulated via partial differential equations (PDEs). By combining a recent spherical surface parametrisation with the advanced non-Lambertian Oren-Nayar reflectance model, we obtain a robust approach that allows to deal with an arbitrary position of the light source while being able to handle rough surfaces and thus more realistic objects at the same time. To our knowledge, the resulting model is currently the most advanced and most flexible approach in the literature on PDE-based perspective SfS. Apart from deriving our model, we also show how the corresponding set of sophisticated Hamilton-Jacobi equations can be efficiently solved by a specifically tailored fast marching scheme. Experiments with medical real-world data demonstrate that our model works in practice and that is offers the desired flexibility. Y1 - 2013 UR - http://www.bmva.org/bmvc/2013/Papers/paper0042/index.html U6 - https://doi.org/10.5244/C.27.42 SP - 42.1 EP - 42.11 PB - BMVA Press ER - TY - CHAP A1 - Chul Ju, Yong A1 - Bruhn, Andrés A1 - Breuß, Michael ED - Aujol, Jean-François ED - Nikolova, Mila ED - Papadakis, Nicolas T1 - Variational Perspective Shape from Shading T2 - Scale Space and Variational Methods in Computer Vision, 5th International Conference, SSVM 2015, Lège-Cap Ferret, France, May 31 - June 4, 2015, Proceedings KW - Shape from shading KW - Variational methods KW - Perspective camera model Y1 - 2015 UR - http://link.springer.com/chapter/10.1007%2F978-3-319-18461-6_43 SN - 978-3-319-18460-9 U6 - https://doi.org/10.1007/978-3-319-18461-6_43 SP - 538 EP - 550 PB - Springer International Publishing CY - Berlin ER - TY - CHAP A1 - Galliani, S. A1 - Ju, Yong Chul A1 - Breuß, Michael A1 - Bruhn, Andrés ED - Kuijper, A. ED - Pock, T. ED - Bredies, K. ED - Bischof, H. T1 - Generalised Perspective Shape from Shading in Spherical Coordinates T2 - Proceedings Fourth International Conference on Scale Space and Variational Methods in Computer Vision, SSVM 2013, Graz, Austria, June 2013 Y1 - 2013 SN - 978-3-642-38266-6 SP - 222 EP - 233 PB - Springer CY - Berlin ER - TY - CHAP A1 - Ju, Yong Chul A1 - Breuß, Michael A1 - Bruhn, Andrés A1 - Galiani, Silvano ED - Browden, R. ED - Collomosse, J. ED - Mikolajczyk, K. T1 - Shape from Shading for Rough Surfaces: Analysis of the Oren-Nayar Model T2 - Proceedings 23rd British Machine Vision Conference, BMVC 2012, Surrey, UK, September 3-7, 2012 Y1 - 2012 SN - 1-901725-46-4 U6 - https://doi.org/10.5244/C.26.104 SP - 104.1 EP - 104.11 PB - BMVA Press ER - TY - GEN A1 - Maurer, Daniel A1 - Ju, Yong Chul A1 - Breuß, Michael A1 - Bruhn, Andrés T1 - Combining Shape from Shading and Stereo: A Joint Variational Method for Estimating Depth, Illumination and Albedo T2 - International Journal of Computer Vision N2 - Shape from shading (SfS) and stereo are two fundamentally different strategies for image-based 3-D reconstruction. While approaches for SfS infer the depth solely from pixel intensities, methods for stereo are based on a matching process that establishes correspondences across images. This difference in approaching the reconstruction problem yields complementary advantages that are worthwhile being combined. So far, however, most “joint” approaches are based on an initial stereo mesh that is subsequently refined using shading information. In this paper we follow a completely different approach. We propose a joint variational method that combines both cues within a single minimisation framework. To this end, we fuse a Lambertian SfS approach with a robust stereo model and supplement the resulting energy functional with a detail-preserving anisotropic second-order smoothness term. Moreover, we extend the resulting model in such a way that it jointly estimates depth, albedo and illumination. This in turn makes the approach applicable to objects with non-uniform albedo as well as to scenes with unknown illumination. Experiments for synthetic and real-world images demonstrate the benefits of our combined approach: They not only show that our method is capable of generating very detailed reconstructions, but also that joint approaches are feasible in practice. KW - Stereo reconstruction KW - Shape from Shading KW - Variational methods KW - Illumination estimation KW - Albedo estimation KW - Joint reasoning Y1 - 2018 U6 - https://doi.org/10.1007/s11263-018-1079-1 SN - 0920-5691 SN - 1573-1405 VL - 126 IS - 12 SP - 1342 EP - 1366 ER - TY - GEN A1 - Maurer, Daniel A1 - Ju, Yong Chul A1 - Breuß, Michael A1 - Bruhn, Andrés T1 - Combining Shape from Shading and Stereo: A Variational Approach for the Joint Estimation of Depth, Illumination and Albedo N2 - Shape from shading (SfS) and stereo are two fundamentally different strategies for image-based 3-D reconstruction. While approaches for SfS infer the depth solely from pixel intensities, methods for stereo are based on a matching process that establishes correspondences across images. In this paper we propose a joint variational method that combines the advantages of both strategies. By integrating recent stereo and SfS models into a single minimisation framework, we obtain an approach that exploits shading information to improve upon the reconstruction quality of robust stereo methods. To this end, we fuse a Lambertian SfS approach with a robust stereo model and supplement the resulting energy functional with a detail-preserving anisotropic second-order smoothness term. Moreover, we extend the novel model in such a way that it jointly estimates depth, albedo and illumination. This in turn makes it applicable to objects with non-uniform albedo as well as to scenes with unknown illumination. Experiments for synthetic and real-world images show the advantages of our combined approach: While the stereo part overcomes the albedo-depth ambiguity inherent to all SfS methods, the SfS part improves the degree of details of the reconstruction compared to pure stereo methods. Y1 - 2016 N1 - Das Poster wurde auf der BMVC in York im September 2016 präsentiert PB - BMVA Press CY - York, UK ER -