We introduce a deep learning approach to automatically generate 3D floor plans and immersive multi-room virtual visit experiences from a small set of co-registered 360° panoramas - down to just one per room. We integrate novel neural networks that leverage panoramic image broad context and large annotated room datasets to build a geometric and visual graph. Nodes represent stereo-viewable multiple-center-of-projection (MCOP) 360° images at the capture locations, while arcs connect them with paths through doors, avoiding clutter and minimizing disocclusions to maximize visual quality. The process starts with depth prediction and floor-plan projection to create a comprehensive but noisy global density map, which is refined via a latent diffusion model. A segmentation network then extracts room layouts, openings, and clutter. This structured representation is lifted to a visual one by creating a 360° stereo-explorable MCOP representation at each node, produced using a view-synthesis network from the original image and its predicted depth map. Arc paths are then computed using an optimization process that considers structural constraints, including openings and obstacles, while minimizing visual discontinuities, occlusions, and disocclusions. Finally, 360° video transitions are synthesized using a specialized view-synthesis network to obtain a fully precomputed WebXR-ready explorable representation that can be efficiently experienced on Head-Mounted-Displays with limited graphics capabilities. The extracted floor plan not only aids in documenting the captured building but can also enhance immersive experiences by serving as a live map of the building. Our experiments show that the method achieves state-of-the-art reconstruction from sparse inputs and supports compelling immersive visits.

We introduce a novel deep neural network designed for fast and structurally consistent monocular 360° depth estimation in indoor settings. Our model generates a spherical depth map from a single gravity-aligned or gravity-rectified equirectangular image, ensuring the predicted depth aligns with the typical depth distribution and structural features of cluttered indoor spaces, which are generally enclosed by walls, floors, and ceilings. By leveraging the distinctive vertical and horizontal patterns found in man-made indoor environments, we propose a streamlined network architecture that incorporates gravity-aligned feature flattening and specialized vision transformers. Through flattening, these transformers fully exploit the omnidirectional nature of the input without requiring patch segmentation or positional encoding. To further enhance structural consistency, we introduce a novel loss function that assesses density map consistency by projecting points from the predicted depth map onto a horizontal plane and a cylindrical proxy. This lightweight architecture requires fewer tunable parameters and computational resources than competing methods. Our comparative evaluation shows that our approach improves depth estimation accuracy while ensuring greater structural consistency compared to existing methods. For these reasons, it promises to be suitable for incorporation in real-time solutions, as well as a building block in more complex structural analysis and segmentation methods.

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.

Today’s Extended Reality (XR) applications that call for specific Diminished Reality (DR) strategies to hide specific classes of objects are increasingly using 360° cameras, which can capture entire areas in a single picture. In this work, we present an interactive-based image processing, editing and rendering system named SPIDER, that takes a spherical 360° indoor scene as input. The system is composed of a novel integrated deep learning architecture for extracting geometric and semantic information of full and empty rooms, based on gated and dilated convolutions, followed by a super-resolution module for improving the resolution of the color and depth signals. The obtained high resolution representations allow users to perform interactive exploration and basic editing operations on the reconstructed indoor scene, namely: (i) rendering of the scene in various modalities (point cloud, polygonal, wireframe) (ii) refurnishing (transferring portions of rooms) (iii) deferred shading through the usage of precomputed normal maps. These kinds of scene editing and manipulations can be used for assessing the inference from deep learning models and enable several Mixed Reality applications in areas such as furniture retails, interior designs, and real estates. Moreover, it can also be useful in data augmentation, arts, designs, and paintings. We report on the performance improvement of the various processing components on public domain spherical image indoor datasets.

We present a new data-driven approach for extracting geometric and structural information from a single spherical panorama of an interior scene, and for using this information to render the scene from novel points of view, enhancing 3D immersion in VR applications. The approach copes with the inherent ambiguities of single-image geometry estimation and novel view synthesis by focusing on the very common case of Atlanta-world interiors, bounded by horizontal floors and ceilings and vertical walls. Based on this prior, we introduce a novel end-to-end deep learning approach to jointly estimate the depth and the underlying room structure of the scene. The prior guides the design of the network and of novel domain-specific loss functions, shifting the major computational load on a training phase that exploits available large-scale synthetic panoramic imagery. An extremely lightweight network uses geometric and structural information to infer novel panoramic views from translated positions at interactive rates, from which perspective views matching head rotations are produced and upsampled to the display size. As a result, our method automatically produces new poses around the original camera at interactive rates, within a working area suitable for producing depth cues for VR applications, especially when using head-mounted displays connected to graphics servers. The extracted floor plan and 3D wall structure can also be used to support room exploration. The experimental results demonstrate that our method provides low-latency performance and improves over current state-of-the-art solutions in prediction accuracy on available commonly used indoor panoramic benchmarks.

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.

We present a shape processing framework for visual exploration of cellular nuclear envelopes extracted from microscopic images arising in histology and neuroscience. The framework is based on a novel shape descriptor of closed contours in 2D and 3D. In 2D, it relies on a geodesically uniform resampling of discrete curves to compute unsigned curvatures at vertices and edges based on discrete differential geometry. Our descriptor is, by design, invariant under translation, rotation, and parameterization. We achieve the latter invariance under parameterization shifts by using elliptic Fourier analysis on the resulting curvature vectors. Uniform scale-invariance is optional and is a result of scaling curvature features to z-scores. We further augment the proposed descriptor with feature coefficients obtained through sparse coding of the extracted cellular structures using K-sparse autoencoders. For the analysis of 3D shapes, we compute mean curvatures based on the Laplace-Beltrami operator on triangular meshes, followed by computing a spherical parameterization through mean curvature flow. Finally, we compute the Spherical Harmonics decomposition to obtain invariant energy coefficients. Our invariant descriptors provide an embedding into a fixed-dimensional feature space that can be used for various applications, e.g., as input features for deep and shallow learning techniques or as input for dimension reduction schemes to provide a visual reference for clustering shape collections. We demonstrate the capabilities of our framework in the context of visual analysis and unsupervised classification of 2D histology images and 3D nuclear envelopes extracted from serial section electron microscopy stacks.

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.

Abstract Creating high‐level structured 3D models of real‐world indoor scenes from captured data is a fundamental task which has important applications in many fields. Given the complexity and variability of interior environments and the need to cope with noisy and partial captured data, many open research problems remain, despite the substantial progress made in the past decade. In this survey, we provide an up‐to‐date integrative view of the field, bridging complementary views coming from computer graphics and computer vision. After providing a characterization of input sources, we define the structure of output models and the priors exploited to bridge the gap between imperfect sources and desired output. We then identify and discuss the main components of a structured reconstruction pipeline, and review how they are combined in scalable solutions working at the building level. We finally point out relevant research issues and analyze research trends.

Abstract We present a novel and light‐weight approach to capture and reconstruct structured 3D models of multi‐room floor plans. Starting from a small set of registered panoramic images, we automatically generate a 3D layout of the rooms and of all the main objects inside. Such a 3D layout is directly suitable for use in a number of real‐world applications, such as guidance, location, routing, or content creation for security and energy management. Our novel pipeline introduces several contributions to indoor reconstruction from purely visual data. In particular, we automatically partition panoramic images in a connectivity graph, according to the visual layout of the rooms, and exploit this graph to support object recovery and rooms boundaries extraction. Moreover, we introduce a plane‐sweeping approach to jointly reason about the content of multiple images and solve the problem of object inference in a top‐down 2D domain. Finally, we combine these methods in a fully automated pipeline for creating a structured 3D model of a multi‐room floor plan and of the location and extent of clutter objects. These contribution make our pipeline able to handle cluttered scenes with complex geometry that are challenging to existing techniques. The effectiveness and performance of our approach is evaluated on both real‐world and synthetic models.

We present a novel approach to automatically recover, from a small set of partially overlapping spherical images, an indoor structure representation in terms of a 3D floor plan registered with a set of 3D environment maps. We introduce several improvements over previous approaches based on color and spatial reasoning exploiting Manhattan world priors. In particular, we introduce a new method for geometric context extraction based on a 3D facet representation, which combines color distribution analysis of individual images with sparse multi-view clues. We also introduce an efficient method to combine the facets from different viewpoints in a single consistent model, taking into the reliability of the facet information. The resulting capture and reconstruction pipeline automatically generates 3D multi-room environments in cases where most previous approaches fail, e.g., in the presence of hidden corners and large clutter, without the need for additional dense 3D data or tools. We demonstrate the effectiveness and performance of our approach on different real-world indoor scenes. Our test data is available to allow further studies and comparisons.

course Share on Mobile graphics Authors: Marco Agus KAUST & CRS4 KAUST & CRS4View Profile , Enrico Gobbetti CRS4 CRS4View Profile , Fabio Marton CRS4 CRS4View Profile , Giovanni Pintore CRS4 CRS4View Profile , Pere-Pau Vázquez UPC UPCView Profile Authors Info & Claims SA '17: SIGGRAPH Asia 2017 CoursesNovember 2017 Article No.: 12Pages 1–259https://doi.org/10.1145/3134472.3134483Published:27 November 2017Publication History 1citation239DownloadsMetricsTotal Citations1Total Downloads239Last 12 Months19Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

We introduce a light-weight automatic method to quickly capture and recover 2.5D multi-room indoor environments scaled to real-world metric dimensions. To minimize the user effort required, we capture and analyze a single omni-directional image per room using widely available mobile devices. Through a simple tracking of the user movements between rooms, we iterate the process to map and reconstruct entire floor plans. In order to infer 3D clues with a minimal processing and without relying on the presence of texture or detail, we define a specialized spatial transform based on catadioptric theory to highlight the room's structure in a virtual projection. From this information, we define a parametric model of each room to formalize our problem as a global optimization solved by Levenberg-Marquardt iterations. The effectiveness of the method is demonstrated on several challenging real-world multi-room indoor scenes.

This paper presents the result of the work achieved in the frame of three successive European Projects, which aimed to build an innovative system to assist security managers in the crisis preparation, training and management phases. The iterative approach of the consortium is presented, as well as the results. A novel interactive and shared Common Operational Picture is proposed which has been validated by three large scale demonstrations. On-going and future work focusing on the security concepts and measures of building interiors is moreover presented.

Abstract We present a GPU accelerated volume ray casting system interactively driving a multi‐user light field display. The display, driven by a single programmable GPU, is based on a specially arranged array of projectors and a holographic screen and provides full horizontal parallax. The characteristics of the display are exploited to develop a specialized volume rendering technique able to provide multiple freely moving naked‐eye viewers the illusion of seeing and manipulating virtual volumetric objects floating in the display workspace. In our approach, a GPU ray‐caster follows rays generated by a multiple‐center‐of‐projection technique while sampling pre‐filtered versions of the dataset at resolutions that match the varying spatial accuracy of the display. The method achieves interactive performance and provides rapid visual understanding of complex volumetric data sets even when using depth oblivious compositing techniques.