Abstract The objective of this thesis is to develop algorithms and software tools for acquiring a structured scene representation from real imagery which can be used for 2-D video coding as well as for interactive 3-D presentation. A new approach will be introduced that recovers visible 3-D structure and texture from one or more partially overlapping uncalibrated views of a scene composed of straight edges. The approach will exploit CAD-like geometric properties which are invariant under perspective projection and are readily identifiable among detectable features in images of man-made scenes (i.e. scenes that contain right angles, parallel edges and planar surfaces). In certain cases, such knowledge of 3-D geometric relationships among detected 2-D features allows recovery of scene structure, intrinsic camera parameters, and camera rotation/position from even a single view. Model-based representations of video offer the promise of ultra-low bandwidths by exploiting the redundancy of information contained in sequences which visualize what is largely a static 3-D world. An algorithm will be proposed that uses a previously recovered estimate of a scene's 3-D structure and texture for the purpose of model-based video coding. Camera focal length and pose will be determined for each frame in a video sequence taken in that known scene. Unmodeled elements (e.g. actors, lighting effects, and noise) will be detected and described in separate compensating signals.

this article are addressed mainly from the computational viewpoint. The primary concerns are how to dene an objective function for the optimal solution for an image analysis problem and how to nd the optimal solution. The reason for dening the solution in an optimization sense is due to various uncertainties in imaging processes. It may be dicult to nd the perfect solution, so we usually look for an optimal one in the sense that an objective, into which constraints are encoded, is optimized

This thesis presents a modeling system that constructs 3D models of particular object classes, such as cups, airplanes, and fish, from 2D sketches. The core of the system is a sketch recognition algorithm that seeks to match the points and curves of a set of given 2D templates to the sketch. The matching process employs an optimization metric that is based on curve feature vectors. The search space of possible correspondences is restricted by encoding knowledge about relative part locations into the 2D template. Once a best-fit template is found, a 3D object is constructed using a series of measurements that are extracted from the labelled 2D sketch. The sketch-recognition and modeling algorithms are applied to sketches of cups and mugs, airplanes, and fish. The system allows non-experts to use drawings to quickly create 3D models of specific object classes.

Occlusion reasoning is a fundamental problem in computer vision. In this paper, we propose an algorithm to recover the occlusion boundaries and depth ordering of free-standing structures in the scene. Rather than viewing the problem as one of pure image processing, our approach employs cues from an estimated surface layout and applies Gestalt grouping principles using a conditional random field (CRF) model. We propose a hierarchical segmentation process, based on agglomerative merging, that re-estimates boundary strength as the segmentation progresses. Our experiments on the Geometric Context dataset validate our choices for features, our iterative refinement of classifiers, and our CRF model. In experiments on the Berkeley Segmentation Dataset, PASCAL VOC 2008, and LabelMe, we also show that the trained algorithm generalizes to other datasets and can be used as an object boundary predictor with figure/ground labels. 1.

We aim to reconstruct three-dimensional polyhedral solids from axonometric-like line sketches. A new approach is proposed to make use of planes of mirror symmetry detected in sketches. Taking into account mirror symmetry of such polyhedra can significantly improve the reconstruction process. Applying symmetry as a regularity in optimisation-based reconstruction is shown to be adequate by itself, without the need for other inflation techniques or regularities. Furthermore, we show how symmetry can be used to reduce the size of the reconstruction problem, leading to a reduction in computing time.

Abstract. In this paper, we present a stochastic algorithm by effective Markov chain Monte Carlo (MCMC) for segmenting and reconstructing 3D scenes. The objective is to segment a range image and its associated reflectance map into a number of surfaces which fit to various 3D surface models and have homogeneous reflectance (material) properties. In comparison to previous work on range image segmentation, the paper makes the following contributions. Firstly, it is aimed at generic natural scenes, indoor and outdoor, which are often much complexer than most of the existing experiments in the “polyhedra world”. Natural scenes require the algorithm to automatically deal with multiple types (families) of surface models which compete to explain the data. Secondly, it integrates the range image with the reflectance map. The latter provides material properties and is especially useful for surface of high specularity, such as glass, metal, ceramics. Thirdly, the algorithm is designed by reversible jump and diffusion Markov chain dynamics and thus achieves globally optimal solutions under the Bayesian statistical framework. Thus it realizes the cue integration and multiple model switching. Fourthly, it adopts two techniques to improve the speed of the Markov chain search: One is a coarse-to-fine strategy and the other are data driven techniques such as edge detection and clustering. The data driven methods provide important information for narrowing the search spaces in a probabilistic fashion. We apply the algorithm to two data sets and the experiments demonstrate robust and satisfactory results on both. Based on the segmentation results, we extend the reconstruction of surfaces behind occlusions to fill in the occluded parts. 1

We aim to reconstruct three-dimensional polyhedra from axonometric line drawings. Existence of mirror symmetry in polyhedra can assist the reconstruction process. We present a new approach for determining planes of mirror symmetry of such polyhedral objects based on prior detection of their planar faces and any axes of symmetry of these faces. The axes are obtained from skewed facial symmetries, for which we also give a new method of determination.

A general-purpose and automatic (or, at least, easy-to-use) system (called REFER) to create 3D geometrical models from 2D sketches, through a geometrical reconstruction process, is our present objective.

Abstract not found

Abstract—Detection of faces in line drawings previous to 3D Reconstruction process is essential for a correct result. In this article a complete state of art about detection of faces in the 3D reconstruction area is given. Then some improvements over the best algorithm are described, and some examples of the results of our approach are shown.