Searching for authors named "Dimitris Samaras" – sorted by Relevance.
-
Research Statement
- onlinear models such as [3]. Instead of extracting the shape parameters directly from these illumination constraints (which is not always possible) ,these constraints are used to provide the necessary generalized forces that will deform our model and estimate the object's 3D shape. This methodology
- Add To MetaCart
-
Estimation of Multiple Directional Light Sources for Synthesis of Mixed Reality Images
- We present a new method for the detection and estimation of multiple directional illuminants, using a single image of any object with known geometry and Lambertian reflectance. We use the resulting highly accurate estimates to modify virtually the illumination and geometry of a real scene and produc
- Cited by 6 (0 self) – Add To MetaCart
-
Estimation of multiple illuminants from a single image of arbitrary known geometry
- Abstract. We present a new method for the detection and estimation of multiple illuminants, using one image of any object withknown geometry and Lambertian reflectance. Our method obviates the need to modify the imaged scene by inserting calibration objects of any particular geometry, relying instea
- Cited by 12 (1 self) – Add To MetaCart
-
Machine learning for clinical diagnosis from functional magnetic resonance imaging
- Functional Magnetic Resonance Imaging (fMRI) has enabled scientists to look into the active human brain. FMRI provides a sequence of 3D brain images with intensities representing brain activations. Standard techniques for fMRI analysis traditionally focused on finding the area of most significant br
- Cited by 8 (3 self) – Add To MetaCart
-
Incorporating Illumination Constraints in Deformable Models for Shape from Shading and Light Direction Estimation
- In this paper we present a method for the integration of nonlinear holonomic constraints in deformable models and its application to the problems of shape and illuminant direction estimation from shading. Experimental results demonstrate that our method performs better than previous Shape from Sh
- Cited by 23 (7 self) – Add To MetaCart
-
Model-based Integration of Visual Cues for Hand Tracking
- We present a model based approach to the integration of multiple cues for tracking high degree of freedom articulated motions. We then apply it to the problem of hand tracking using a single camera sequence. Hand tracking is particularly challenging because of occlusions, shading variations, and the
- Cited by 4 (0 self) – Add To MetaCart
-
Shape reconstruction from 3D and 2D data using PDE-based deformable surfaces
- Abstract. In this paper, we propose a new PDE-based methodology for deformable surfaces that is capable of automatically evolving its shape to capture the geometric boundary of the data and simultaneously discover its underlying topological structure. Our model can handle multiple types of data (suc
- Cited by 23 (1 self) – Add To MetaCart
-
Using Multiple Cues for Hand Tracking and Model Refinement
- We present a model based approach to the integration of multiple cues for tracking high degree of freedom articulated motions and model refinement. We then apply it to the problem of hand tracking using a single camera sequence. Hand tracking is particularly challenging because of occlusions, shadin
- Cited by 21 (2 self) – Add To MetaCart
-
Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics
- Abstract—In this paper, we propose two novel methods for face recognition under arbitrary unknown lighting by using spherical harmonics illumination representation, which require only one training image per subject and no 3D shape information. Our methods are based on the recent result which demonst
- Cited by 9 (1 self) – Add To MetaCart
-
Topology Cuts: A Novel Min-Cut/Max-Flow Algorithm for Topology Preserving Segmentation in N-D Images
- Topology is an important prior in many image segmentation tasks. In this paper, we design and implement a novel graph-based min-cut/max-flow algorithm that incorporates topology priors as global constraints. We show that optimization of the energy function we consider here is NPhard. However, our al
- Cited by 2 (0 self) – Add To MetaCart

