The definition of a good view of a 3D scene is highly subjective and strongly depends on both the scene content and the 3D application. Usually, camera placement is performed directly by the user, and that task may be laborious. Existing automatic virtual cameras guide the user by optimizing a single rule, e.g. maximizing the visible silhouette or the projected area. However, the use of a static pre-defined rule may fail in respecting the user's subjective understanding of the scene. This work introduces intelligent design galleries, a learning approach for subjective problems such as the camera placement. The interaction of the user with a design gallery teaches a statistical learning machine. The trained machine can then imitate the user, either by pre-selecting good views or by automatically placing the camera. The learning process relies on a Support Vector Machines for classifying views from a collection of descriptors, ranging from 2D image quality to 3D features visibility. Experiments of the automatic camera placement demonstrate that the proposed technique is efficient and handles scenes with occlusion and high depth complexities. This work also includes user validations of the intelligent gallery interface.

This work emerged from the following observation: usual search procedures for octrees start from the root to retrieve the data stored at the leaves. But as the leaves are the farthest nodes to the root, why start from the root? With usual octree representations, there is no other way to access a leaf. However, hashed octrees allow direct access to any node, given its position in space and its depth in the octree. Search procedures take the position as an input, but the depth remains unknown. This work proposes to estimate the depth of an arbitrary node through a statistical optimization of the average cost of search procedures. As the highest costs of these algorithms are obtained when starting from the root, this method improves on both the memory footprint by the use of hashed octrees, and execution time through the proposed optimization.

No abstract

No abstract

Figure 1. Reconstruction of a real 3D velocity field captured by a PIV device with sparse, irregular sampling: magnitude (left) and phase (right).Abstract-Sampled vector fields generally appear as measurements of real phenomena. They can be obtained by the use of a Particle Image Velocimetry acquisition device, or as the result of a physical simulation, such as a fluid flow simulation, among many examples. This paper proposes to formulate the unstructured vector field reconstruction and approximation through Machine-Learning. The machine learns from the samples a global vector field estimation function that could be evaluated at arbitrary points from the whole domain. Using an adaptation of the Support Vector Regression method for multi-scale analysis, the proposed method provides a global, analytical expression for the reconstructed vector field through an efficient non-linear optimization. Experiments on artificial and real data show a statistically robust behavior of the proposed technique.