We introduce a novel end-to-end deep-learning solution for rapidly estimating a dense spherical depth map of an indoor environment. Our input is a single equirectangular image registered with a sparse depth map, as provided by a variety of common capture setups. Depth is inferred by an efficient and lightweight single-branch network, which employs a dynamic gating system to process together dense visual data and sparse geometric data. We exploit the characteristics of typical man-made environments to efficiently compress multi-resolution features and find short- and long-range relations among scene parts. Furthermore, we introduce a new augmentation strategy to make the model robust to different types of sparsity, including those generated by various structured light sensors and LiDAR setups. The experimental results demonstrate that our method provides interactive performance and outperforms state-of-the-art solutions in computational efficiency, adaptivity to variable depth sparsity patterns, and prediction accuracy for challenging indoor data, even when trained solely on synthetic data without any fine tuning.

Nowadays 360° cameras, capable to capture full environments in a single shot, are increasingly being used in a variety of Extended Reality (XR) applications that require specific Diminished Reality (DR) techniques to conceal selected classes of objects. In this work, we present a new data-driven approach that, from an input 360° image of a furnished indoor space automatically returns, with very low latency, an omnidirectional photorealistic view and architecturally plausible depth of the same scene emptied of all clutter. Contrary to recent data-driven inpainting methods that remove single user-defined objects based on their semantics, our approach is holistically applied to the entire scene, and is capable to separate the clutter from the architectural structure in a single step. By exploiting peculiar geometric features of the indoor environment, we shift the major computational load on the training phase and having an extremely lightweight network at prediction time. Our end-to-end approach starts by calculating an attention mask of the clutter in the image based on the geometric difference between full and empty scene. This mask is then propagated through gated convolutions that drive the generation of the output image and its depth. Returning the depth of the resulting structure allows us to exploit, during supervised training, geometric losses of different orders, including robust pixel-wise geometric losses and high-order 3D constraints typical of indoor structures. The experimental results demonstrate that our method provides interactive performance and outperforms current state-of-the-art solutions in prediction accuracy on available commonly used indoor panoramic benchmarks. In addition, our method presents consistent quality results even for scenes captured in the wild and for data for which there is no ground truth to support supervised training.

We introduce a novel deep neural network to estimate a depth map from a single monocular indoor panorama. The network directly works on the equirectangular projection, exploiting the properties of indoor 360° images. Starting from the fact that gravity plays an important role in the design and construction of man-made indoor scenes, we propose a compact representation of the scene into vertical slices of the sphere, and we exploit long- and short-term relationships among slices to recover the equirectangular depth map. Our design makes it possible to maintain high-resolution information in the extracted features even with a deep network. The experimental results demonstrate that our method outperforms current state-of-the-art solutions in prediction accuracy, particularly for real-world data.

Recovering the 3D shape of the bounding permanent surfaces of a room from a single image is a key component of indoor reconstruction pipelines. In this article, we introduce a novel deep learning technique capable to produce, at interactive rates, a tessellated bounding 3D surface from a single 360° image. Differently from prior solutions, we fully address the problem in 3D, significantly expanding the reconstruction space of prior solutions. A graph convolutional network directly infers the room structure as a 3D mesh by progressively deforming a graph-encoded tessellated sphere mapped to the spherical panorama, leveraging perceptual features extracted from the input image. Important 3D properties of indoor environments are exploited in our design. In particular, gravity-aligned features are actively incorporated in the graph in a projection layer that exploits the recent concept of multi head self-attention, and specialized losses guide towards plausible solutions even in presence of massive clutter and occlusions. Extensive experiments demonstrate that our approach outperforms current state of the art methods in terms of accuracy and capability to reconstruct more complex environments.

The significance and benefits of addressing classification tasks in Big Data applications is beyond any doubt. To do so, learning algorithms must be scalable to cope with such a high volume of data. The most suitable option to reach this objective is by using a MapReduce programming scheme, in which algorithms are automatically executed in a distributed and fault tolerant way. Among different available tools that support this framework, Spark has emerged as a “de facto” solution when using iterative approaches. In this work, our goal is to design and implement an Evolutionary Fuzzy Rule Selection algorithm within a Spark environment. To do so, we build different local rule bases within each Map Task that are later optimized by means of a genetic process. With this procedure, we seek to minimize the total number of rules that are gathered by each Reduce task to obtain a compact and accurate Fuzzy Rule Based Classification System. In particular, we set the experimental framework in the scenario of imbalanced classification. Therefore, the final objective will be analyzing the best synergy between the novel Evolutionary Fuzzy Rule Selection algorithm and the solutions applied to cope with skewed class distributions, namely cost-sensitive learning, random under-sampling and random-oversampling.