George Vogiatzis

I am a senior research scientist at the Toshiba Research Laboratory in Cambridge, UK where I am a member of the Computer Vision Group. Prior to joining Toshiba Research I was a PhD student in in the Machine Intelligence Laboratory in the Department of Engineering, University of Cambridge. As an undergraduate I studied Mathematics and Computer Science at Imperial College, London. I also currently hold a junior research fellowship in Wolfson College.

My research is focused on algorithms for obtaining a complete, detailed, three-dimensional model of a real object from a collection of digital photographs. 3D computer models are a vital part of a wide range of disciplines, from the study of sculpture and architecture to archaeology, structural engineering and computer graphics. The owner of such a digital copy of an object is able to inspect details of the object from any viewpoint, measure geometric properties such as angles, lengths and volumes or reproduce it in a different material.

Using Multiple Hypotheses to Improve Depth-Maps for Multi-View Stereo
N. Campbell, G. Vogiatzis, C. Hernández and R. Cipolla. In Proceedings European Conference of Computer Vision (ECCV), 2008.

This paper proposes an improvement to a large class of Multi-View Stereo algorithms that fuse stereo depth maps. We show that if individual depth-maps are filtered for outliers prior to the fusion stage, good performance can be maintained in sparse data-sets. Our strategy is to collect a list of good hypotheses for the depth of each pixel. We then chose the optimal depth for each pixel by enforcing consistency between neighbouring pixels in a depth-map. A crucial element of the fitering stage is the introduction of a possible unknown depth hypothesis for each pixel, which is selected by the algorithm when no consistent depth can be chosen. This pre-processing of the depth-maps allows the global fusion stage to operate on fewer outliers and consequently improve the performance under sparsity of data.

Shadows in Three-Source Photometric Stereo
C. Hernández, G. Vogiatzis and R. Cipolla. In Proceedings European Conference of Computer Vision (ECCV), 2008.

Shadows present a significant challenge for Photometric Stereo methods. When four or more images are available, local surface orientation is overdetermined and the shadowed pixels can be discarded. In this paper we look at the challenging case when only three images under three different illuminations are available. In this case, when one of the three pixel intensity constraints is missing due to shadow, a 1 dof ambiguity per pixel arises. We show that using integrability one can resolve this ambiguity and use the remaining two constraints to reconstruct the geometry in the shadow regions. As the problem becomes ill-posed in the presence of noise, we describe a regularization scheme that improves the numerical performance of the algorithm while preserving data.

Non-rigid Photometric Stereo with Colored Lights
C. Hernández, G. Vogiatzis, G. Brostow, B. Stenger and R. Cipolla. In Proceedings IEEE International Conference of Computer Vision (ICCV), 2007.

When three lights illuminate a surface from three different angles and with three different colors, there is a one-to-one mapping between the RGB color measured by a camera and the surface orientation. If we illuminate a complex object under this setup, we can invert the mapping to get surface orientations from an RGB image, then integrate those to get a depth-map. In this paper, this idea, previously used only with static objects, is applied to the reconstruction of a deforming object, such as a moving cloth. We capture color videos of complex motions of fabrics, from which we extract sequences of depth maps. We propose a simple scheme with which these depth maps can be registered to a canonical pose and this allows complex applications such as texture mapping or avatar skinning. A video showing the system in action can be found in the following links: short avi, longer version and from YouTube part 1 and part 2.

Multi-view Photometric Stereo
C. Hernández, G. Vogiatzis and R. Cipolla. To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2008.

This is an extension and consolidation of our CVPR 2006 work on multi-view photometric stereo. The main difference of this paper is that significant albedo variations in the surface of the reconstructed object can be tolerated. In the case where albedo variation is present on the object, we can usually obtain reconstructions with classic multi-view dense stereo. We show however, how our work produces results of much higher geometric detail than multi-view stereo, by exploiting the change in illumination. An earlier version of this work appeared in

Lighting-up geometry: accurate 3D modelling of museum artifacts with a torch and a camera
G. Vogiatzis, C. Hernández and R. Cipolla. In Eurographics 2006, Short papers, pages 85-88, 2006. (talk)

Automatic 3D Object Segmentation in Multiple Views using Volumetric Graph-Cuts
N. Campbell, G. Vogiatzis, C. Hernandez and R. Cipolla. In Proceedings 18th British Machine Vision Conference (BMVC), 2007 vol. 1, pages 530-539, 2007. (talk)

Many multi-view stereo methods are faced with the problem of segmenting 20-100 calibrated images of a 3D object. These segmentations are used to create a visual hull which is a first approximation to the object's geometry. In this paper we propose a simple technique for automatically segmenting these images. Our idea is based on two observations: (1) In each image the camera will usually fixate on the object of interest and (2) the segmentations are not independent because of the silhouette coherence constraint. We use (1) to initalise an object color model. We then perform a series of simultaneous segmentations using (2). In each iteration we update the color model based on previous results. The process converges to the correct segmentations after just a few iterations.

Multi-view Stereo via Volumetric Graph-cuts and Occlusion Robust Photo-Consistency
G. Vogiatzis, C. Hernández, P. H. S. Torr, and R. Cipolla. IEEE Transactions in Pattern Analysis and Machine Intelligence (PAMI), vol. 29, no. 12, pages 2241-2246, Dec., 2007.

Here we revisit our CVPR 2005 work and develop a much improved formulation. The object surface is defined as a partition of 3D space into 'inside' and 'outside' regions. The cost functional, which we optimise using Graph-cuts, is a combination of a simple balooning force and an occlusion-independent Normalised Cross Correlation cost. The advantages of our approach are the following: (1) Objects of arbitrary topology can be fully represented and computed as a single surface with no self-intersections. (2) The representation and geometric regularisation is image and viewpoint independent. (3) Global optimisation is computationally tractable, using existing max-flow algorithms.

Probabilistic visibility for multi-view stereo
C. Hernández, G. Vogiatzis and R. Cipolla. In Proceedings IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2007.

In this work we explore how the photo-consistency criterion can be used to obtain a likelihood for a given 3D location being 'empty'. We observe that if a 3D point is considered as photo-consistent from a certain camera, then all 3D locations between that point and the camera are likely to be empty. In fact the degree of likelihood for 'emptiness' is related to the degree of photo-consistency. We formalise this observation probabilistically and show how it can be used to reconstruct difficult concavities in objects.

Reconstruction in the Round Using Photometric Normals and Silhouettes
G. Vogiatzis, C. Hernández and R. Cipolla. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1847-1854, 2006.

In this work we have obtained full 3D reconstructions of single-albedo, near-Lambertian objects such as white porcelain from 36 views under changing but unknown lighting (single distant light-source assumed). This work is the first to generalise uncalibrated photometric stereo in the multi-view setting. For a more detailed look at some other models we reconstructed using this technique, look here. All you will need is a java enabled browser.

Using Frontier Points to Recover Shape, Reflectance and Illumination
G. Vogiatzis, P. Favaro and R. Cipolla. In Proceedings IEEE International Conference of Computer Vision (ICCV), pages 228-235, 2005.

Frontier Points are a robust geometrical feature extracted from the silhouettes. They are points on the surface of the object with a known 3D location and known local surface orientation. In this paper we have shown how they can be used to recover information about the surface reflectance of the object as well as illumination.

Multi-view stereo via Volumetric Graph-cuts
G. Vogiatzis, P.H.S. Torr and R. Cipolla. In Proceedings IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 391-398, 2005. (talk)

The object surface is defined as a boundary separating the Visual Hull surface from an inner surface at a constant offset from and inside the Visual Hull. The volume between these two surfaces is discretized into voxels and for each voxel we compute a photo-consistency cost. Using Graph-Cuts and a specially defined weighted graph, we compute the surface that optimally separates voxels inside and outside the scene.

Reconstructing Relief Surfaces
G. Vogiatzis, P.H.S. Torr, S. Seitz and R. Cipolla In Proceedings 15th British Machine Vision Conference (BMVC), pages 117-126, 2004. (talk)

The object surface is defined as a height field on top of a coarse approximation of the scene surface (typically the visual hull). The height field is formulated as a Markov Random Field incorporating photo-consistency and surface smoothness constraints. The resulting cost function is optimized using Loopy Belief Propagation.