HDR-Net-Fusion: Real-time 3D dynamic scene reconstruction with a hierarchical deep reinforcement network

Reconstructing dynamic scenes with commodity depth cameras has many applications in computer graphics, computer vision, and robotics. However, due to the presence of noise and erroneous observations from data capturing devices and the inherently ill-posed nature of non-rigid registration with insufficient information, traditional approaches often produce low-quality geometry with holes, bumps, and misalignments. We propose a novel 3D dynamic reconstruction system, named HDR-Net-Fusion, which learns to simultaneously reconstruct and refine the geometry on the fly with a sparse embedded deformation graph of surfels, using a hierarchical deep reinforcement (HDR) network. The latter comprises two parts: a global HDR-Net which rapidly detects local regions with large geometric errors, and a local HDR-Net serving as a local patch refinement operator to promptly complete and enhance such regions. Training the global HDR-Net is formulated as a novel reinforcement learning problem to implicitly learn the region selection strategy with the goal of improving the overall reconstruction quality. The applicability and efficiency of our approach are demonstrated using a large-scale dynamic reconstruction dataset. Our method can reconstruct geometry with higher quality than traditional methods.

An unsupervised approach to disjointness learning based on terminological cluster trees

In the context of the Semantic Web regarded as a Web of Data, research efforts have been devoted to improving the quality of the ontologies that are used as vocabularies to enable complex services based on automated reasoning. From various surveys it emerges that many domains would require better ontologies that include non-negligible constraints for properly conveying the intended semantics. In this respect, disjointness axioms are representative of this general problem: these axioms are essential for making the negative knowledge about the domain of interest explicit yet they are often overlooked during the modeling process (thus affecting the efficacy of the reasoning services). To tackle this problem, automated methods for discovering these axioms can be used as a tool for supporting knowledge engineers in modeling new ontologies or evolving existing ones. The current solutions, either based on statistical correlations or relying on external corpora, often do not fully exploit the terminology. Stemming from this consideration, we have been investigating on alternative methods to elicit disjointness axioms from existing ontologies based on the induction of terminological cluster trees, which are logic trees in which each node stands for a cluster of individuals which emerges as a sub-concept. The growth of such trees relies on a divide-and-conquer procedure that assigns, for the cluster representing the root node, one of the concept descriptions generated via a refinement operator and selected according to a heuristic based on the minimization of the risk of overlap between the candidate sub-clusters (quantified in terms of the distance between two prototypical individuals). Preliminary works have showed some shortcomings that are tackled in this paper. To tackle the task of disjointness axioms discovery we have extended the terminological cluster tree induction framework with various contributions: 1) the adoption of different distance measures for clustering the individuals of a knowledge base; 2) the adoption of different heuristics for selecting the most promising concept descriptions; 3) a modified version of the refinement operator to prevent the introduction of inconsistency during the elicitation of the new axioms. A wide empirical evaluation showed the feasibility of the proposed extensions and the improvement with respect to alternative approaches.

Dynamic networks of heterogeneous timed machines

We present an algebra of discrete timed input/output automata that may execute in the context of different clock granularities – which we call timed machines; this algebra includes a refinement operator through which a machine can be extended with new states and transitions in order to accommodate a finer clock granularity as required to interoperate with other machines, and an extension of the traditional product of timed input–output automata to the situation in which the granularities of the two machines are not the same. Over this algebra, we then define an algebra of networks of timed machines that includes operations through which networks can be modified at run time, thus offering a model for systems of interconnected components that can dynamically bind to other systems and, therefore, cannot be adjusted at design time to ensure that they operate in a timed homogeneous setting. We investigate important properties of timed machines such as consistency – in the sense that a machine can be ensured to generate a non-empty language, and feasibility – in the sense that a machine can be ensured to generate a non-empty language no matter what inputs it receives, and propose techniques for checking if timed machines are consistent or are feasible. We generalise those properties to networks of timed machines, and investigate how consistency and feasibility of networks can be proved through properties that can be checked at design time without having to compute, at run time, the product of the machines that operate on those networks, which would not be practical.