Dimitrios Zarpalas

Sotiris Karavarsamis, Alexandros Doumanoglou, Konstantinos Konstantoudakis et al.

We present the Cross-stitched Multi-task Unified Dual Recursive Network (CMUDRN) model targeting the task of unified deraining and desnowing in a multi-task learning setting. This unified model borrows from the basic Dual Recursive Network (DRN) architecture developed by Cai et al. The proposed model makes use of cross-stitch units that enable multi-task learning across two separate DRN models, each tasked for single image deraining and desnowing, respectively. By fixing cross-stitch units at several layers of basic task-specific DRN networks, we perform multi-task learning over the two separate DRN models. To enable blind image restoration, on top of these structures we employ a simple neural fusion scheme which merges the output of each DRN. The separate task-specific DRN models and the fusion scheme are simultaneously trained by enforcing local and global supervision. Local supervision is applied on the two DRN submodules, and global supervision is applied on the data fusion submodule of the proposed model. Consequently, we both enable feature sharing across task-specific DRN models and control the image restoration behavior of the DRN submodules. An ablation study shows the strength of the hypothesized CMUDRN model, and experiments indicate that its performance is comparable or better than baseline DRN models on the single image deraining and desnowing tasks. Moreover, CMUDRN enables blind image restoration for the two underlying image restoration tasks, by unifying task-specific image restoration pipelines via a naive parametric fusion scheme. The CMUDRN implementation is available at https://github.com/VCL3D/CMUDRN.

Nikolaos Zioulis, Georgios Albanis, Petros Drakoulis et al.

In this work we introduce a biologically inspired long-range skip connection for the UNet architecture that relies on the perceptual illusion of hybrid images, being images that simultaneously encode two images. The fusion of early encoder features with deeper decoder ones allows UNet models to produce finer-grained dense predictions. While proven in segmentation tasks, the network's benefits are down-weighted for dense regression tasks as these long-range skip connections additionally result in texture transfer artifacts. Specifically for depth estimation, this hurts smoothness and introduces false positive edges which are detrimental to the task due to the depth maps' piece-wise smooth nature. The proposed HybridSkip connections show improved performance in balancing the trade-off between edge preservation, and the minimization of texture transfer artifacts that hurt smoothness. This is achieved by the proper and balanced exchange of information that Hybrid-Skip connections offer between the high and low frequency, encoder and decoder features, respectively.

Nikolaos Zioulis, Federico Alvarez, Dimitrios Zarpalas et al.

Spherical cameras capture scenes in a holistic manner and have been used for room layout estimation. Recently, with the availability of appropriate datasets, there has also been progress in depth estimation from a single omnidirectional image. While these two tasks are complementary, few works have been able to explore them in parallel to advance indoor geometric perception, and those that have done so either relied on synthetic data, or used small scale datasets, as few options are available that include both layout annotations and dense depth maps in real scenes. This is partly due to the necessity of manual annotations for room layouts. In this work, we move beyond this limitation and generate a 360 geometric vision (360V) dataset that includes multiple modalities, multi-view stereo data and automatically generated weak layout cues. We also explore an explicit coupling between the two tasks to integrate them into a singleshot trained model. We rely on depth-based layout reconstruction and layout-based depth attention, demonstrating increased performance across both tasks. By using single 360 cameras to scan rooms, the opportunity for facile and quick building-scale 3D scanning arises.

Alexandros Doumanoglou, Stylianos Asteriadis, Dimitrios Zarpalas

An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work supports that deep representations are linearly separable with respect to their concept label, implying that the feature space has directions where intermediate representations may be projected onto, to become more understandable. These directions are called interpretable, and when considered as a set, they may form an interpretable feature space basis. Compared to previous top-down probing approaches which use concept annotations to identify the interpretable directions one at a time, in this work, we take a bottom-up approach, identifying the directions from the structure of the feature space, collectively, without relying on supervision from concept labels. Instead, we learn the directions by optimizing for a sparsity property that holds for any interpretable basis. We experiment with existing popular CNNs and demonstrate the effectiveness of our method in extracting an interpretable basis across network architectures and training datasets. We make extensions to existing basis interpretability metrics and show that intermediate layer representations become more interpretable when transformed with the extracted bases. Finally, we compare the bases extracted with our method with the bases derived with supervision and find that, in one aspect, unsupervised basis extraction has a strength that constitutes a limitation of learning the basis with supervision, and we provide potential directions for future research.

Anastasios Tsalakopoulos, Angelos Kanlis, Evangelos Chatzis et al.

We introduce Geo-NVS-w, a geometry-aware framework for high-fidelity novel view synthesis from unstructured, in-the-wild image collections. While existing in-the-wild methods already excel at novel view synthesis, they often lack geometric grounding on complex surfaces, sometimes producing results that contain inconsistencies. Geo-NVS-w addresses this limitation by leveraging an underlying geometric representation based on a Signed Distance Function (SDF) to guide the rendering process. This is complemented by a novel Geometry-Preservation Loss which ensures that fine structural details are preserved. Our framework achieves competitive rendering performance, while demonstrating a 4-5x reduction reduction in energy consumption compared to similar methods. We demonstrate that Geo-NVS-w is a robust method for in-the-wild NVS, yielding photorealistic results with sharp, geometrically coherent details.

Vasileios Gkitsas, Nikolaos Zioulis, Vladimiros Sterzentsenko et al.

The task of transforming a furnished room image into a background-only is extremely challenging since it requires making large changes regarding the scene context while still preserving the overall layout and style. In order to acquire photo-realistic and structural consistent background, existing deep learning methods either employ image inpainting approaches or incorporate the learning of the scene layout as an individual task and leverage it later in a not fully differentiable semantic region-adaptive normalization module. To tackle these drawbacks, we treat scene layout generation as a feature linear transformation problem and propose a simple yet effective adjusted fully differentiable soft semantic region-adaptive normalization module (softSEAN) block. We showcase the applicability in diminished reality and depth estimation tasks, where our approach besides the advantages of mitigating training complexity and non-differentiability issues, surpasses the compared methods both quantitatively and qualitatively. Our softSEAN block can be used as a drop-in module for existing discriminative and generative models. Implementation is available on vcl3d.github.io/PanoDR/.

Anargyros Chatzitofis, Leonidas Saroglou, Prodromos Boutis et al.

We introduce HUMAN4D, a large and multimodal 4D dataset that contains a variety of human activities simultaneously captured by a professional marker-based MoCap, a volumetric capture and an audio recording system. By capturing 2 female and $2$ male professional actors performing various full-body movements and expressions, HUMAN4D provides a diverse set of motions and poses encountered as part of single- and multi-person daily, physical and social activities (jumping, dancing, etc.), along with multi-RGBD (mRGBD), volumetric and audio data. Despite the existence of multi-view color datasets captured with the use of hardware (HW) synchronization, to the best of our knowledge, HUMAN4D is the first and only public resource that provides volumetric depth maps with high synchronization precision due to the use of intra- and inter-sensor HW-SYNC. Moreover, a spatio-temporally aligned scanned and rigged 3D character complements HUMAN4D to enable joint research on time-varying and high-quality dynamic meshes. We provide evaluation baselines by benchmarking HUMAN4D with state-of-the-art human pose estimation and 3D compression methods. For the former, we apply 2D and 3D pose estimation algorithms both on single- and multi-view data cues. For the latter, we benchmark open-source 3D codecs on volumetric data respecting online volumetric video encoding and steady bit-rates. Furthermore, qualitative and quantitative visual comparison between mesh-based volumetric data reconstructed in different qualities showcases the available options with respect to 4D representations. HUMAN4D is introduced to the computer vision and graphics research communities to enable joint research on spatio-temporally aligned pose, volumetric, mRGBD and audio data cues. The dataset and its code are available https://tofis.github.io/myurls/human4d.

Vladimiros Sterzentsenko, Leonidas Saroglou, Anargyros Chatzitofis et al.

Depth perception is considered an invaluable source of information for various vision tasks. However, depth maps acquired using consumer-level sensors still suffer from non-negligible noise. This fact has recently motivated researchers to exploit traditional filters, as well as the deep learning paradigm, in order to suppress the aforementioned non-uniform noise, while preserving geometric details. Despite the effort, deep depth denoising is still an open challenge mainly due to the lack of clean data that could be used as ground truth. In this paper, we propose a fully convolutional deep autoencoder that learns to denoise depth maps, surpassing the lack of ground truth data. Specifically, the proposed autoencoder exploits multiple views of the same scene from different points of view in order to learn to suppress noise in a self-supervised end-to-end manner using depth and color information during training, yet only depth during inference. To enforce selfsupervision, we leverage a differentiable rendering technique to exploit photometric supervision, which is further regularized using geometric and surface priors. As the proposed approach relies on raw data acquisition, a large RGB-D corpus is collected using Intel RealSense sensors. Complementary to a quantitative evaluation, we demonstrate the effectiveness of the proposed self-supervised denoising approach on established 3D reconstruction applications. Code is avalable at https://github.com/VCL3D/DeepDepthDenoising

Grigorios Aris Cheimariotis, Antonis Karakottas, Vangelis Chatzis et al.

Data valuation and monetization are becoming increasingly important across domains such as eXtended Reality (XR) and digital media. In the context of 3D scene reconstruction from a set of images -- whether casually or professionally captured -- not all inputs contribute equally to the final output. Neural Radiance Fields (NeRFs) enable photorealistic 3D reconstruction of scenes by optimizing a volumetric radiance field given a set of images. However, in-the-wild scenes often include image captures of varying quality, occlusions, and transient objects, resulting in uneven utility across inputs. In this paper we propose a method to quantify the individual contribution of each image to NeRF-based reconstructions of in-the-wild image sets. Contribution is assessed through reconstruction quality metrics based on PSNR and MSE. We validate our approach by removing low-contributing images during training and measuring the resulting impact on reconstruction fidelity.

Alexandros Doumanoglou, Kurt Driessens, Dimitrios Zarpalas

Empirical evidence shows that deep vision networks represent concepts as directions in latent space, vectors we call concept embeddings. Each concept has a latent factor-a scalar-indicating its presence in an input patch. For a given patch, multiple latent factors are encoded into a compact representation by linearly combining concept embeddings, with the factors as coefficients. Since these embeddings enable such encoding, we call them encoding directions. A latent factor can be recovered via the inner product with a filter, a vector we call a decoding direction. These encoding-decoding direction pairs are not directly accessible, but recovering them helps open the black box of deep networks, enabling understanding, debugging, and improving models. Decoder directions attribute meaning to latent codes, while encoding directions assess concept influence on predictions, with both enabling model correction by unlearning irrelevant concepts. Unlike prior matrix decomposition, autoencoder, or dictionary learning methods that rely on feature reconstruction, we propose a new perspective: decoding directions are identified via directional clustering of activations, and encoding directions are estimated with signal vectors under a probabilistic view. We further leverage network weights through a novel technique, Uncertainty Region Alignment, which reveals interpretable directions affecting predictions. Our analysis shows that (a) on synthetic data, our method recovers ground-truth direction pairs; (b) on real data, decoding directions map to monosemantic, interpretable concepts and outperform unsupervised baselines; and (c) signal vectors faithfully estimate encoding directions, validated via activation maximization. Finally, we demonstrate applications in understanding global model behavior, explaining individual predictions, and intervening to produce counterfactuals or correct errors.

Yannis Kaltampanidis, Alexandros Doumanoglou, Dimitrios Zarpalas

Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, including image classification and segmentation, both in standard and few-shot downstream contexts. Two pre-training objectives dominate the landscape of SSL techniques: Contrastive Learning and Masked Image Modeling. Features (or tokens) extracted from the final transformer attention block -- specifically, the keys, queries, and values -- as well as features obtained after the final block's feed-forward layer, have become a common foundation for addressing downstream tasks. However, in many existing approaches, these pre-trained ViT features are further processed through additional transformation layers, often involving lightweight heads or combined with distillation, to achieve superior task performance. Although such methods can improve task outcomes, to the best of our knowledge, a comprehensive analysis of the intrinsic representation capabilities of unaltered ViT features has yet to be conducted. This study aims to bridge this gap by systematically evaluating the use of these unmodified features across image classification and segmentation tasks, in both standard and few-shot contexts. The classification and segmentation rules that we use are either hyperplane based (as in logistic regression) or cosine-similarity based, both of which rely on the presence of interpretable directions in the ViT's latent space. Based on the previous rules and without the use of additional feature transformations, we conduct an analysis across token types, tasks, and pre-trained ViT models. This study provides insights into the optimal choice for token type and decision rule based on the task, context, and the pre-training objective, while reporting detailed findings on two widely-used datasets.

Asterios Reppas, Grigorios-Aris Cheimariotis, Panos K. Papadopoulos et al.

Precise camera localization is a critical task in XR applications and robotics. Using only the camera captures as input to a system is an inexpensive option that enables localization in large indoor and outdoor environments, but it presents challenges in achieving high accuracy. Specifically, camera relocalization methods, such as Absolute Pose Regression (APR), can localize cameras with a median translation error of more than $0.5m$ in outdoor scenes. This paper presents HAL-NeRF, a high-accuracy localization method that combines a CNN pose regressor with a refinement module based on a Monte Carlo particle filter. The Nerfacto model, an implementation of Neural Radiance Fields (NeRFs), is used to augment the data for training the pose regressor and to measure photometric loss in the particle filter refinement module. HAL-NeRF leverages Nerfacto's ability to synthesize high-quality novel views, significantly improving the performance of the localization pipeline. HAL-NeRF achieves state-of-the-art results that are conventionally measured as the average of the median per scene errors. The translation error was $0.025m$ and the rotation error was $0.59$ degrees and 0.04m and 0.58 degrees on the 7-Scenes dataset and Cambridge Landmarks datasets respectively, with the trade-off of increased computational time. This work highlights the potential of combining APR with NeRF-based refinement techniques to advance monocular camera relocalization accuracy.

Georgios Albanis, Nikolaos Zioulis, Petros Drakoulis et al.

In this work we contribute a distribution shift benchmark for a computer vision task; monocular depth estimation. Our differentiation is the decomposition of the wider distribution shift of uncontrolled testing on in-the-wild data, to three distinct distribution shifts. Specifically, we generate data via synthesis and analyze them to produce covariate (color input), prior (depth output) and concept (their relationship) distribution shifts. We also synthesize combinations and show how each one is indeed a different challenge to address, as stacking them produces increased performance drops and cannot be addressed horizontally using standard approaches.

Anargyros Chatzitofis, Nikolaos Zioulis, Georgios Nikolaos Albanis et al.

A series of 2D (and 3D) keypoint estimation tasks are built upon heatmap coordinate representation, i.e. a probability map that allows for learnable and spatially aware encoding and decoding of keypoint coordinates on grids, even allowing for sub-pixel coordinate accuracy. In this report, we aim to reproduce the findings of DARK that investigated the 2D heatmap representation by highlighting the importance of the encoding of the ground truth heatmap and the decoding of the predicted heatmap to keypoint coordinates. The authors claim that a) a more principled distribution-aware coordinate decoding method overcomes the limitations of the standard techniques widely used in the literature, and b), that the reconstruction of heatmaps from ground-truth coordinates by generating accurate and continuous heatmap distributions lead to unbiased model training, contrary to the standard coordinate encoding process that quantizes the keypoint coordinates on the resolution of the input image grid.

Anargyros Chatzitofis, Dimitrios Zarpalas, Stefanos Kollias et al.

In this paper, a marker-based, single-person optical motion capture method (DeepMoCap) is proposed using multiple spatio-temporally aligned infrared-depth sensors and retro-reflective straps and patches (reflectors). DeepMoCap explores motion capture by automatically localizing and labeling reflectors on depth images and, subsequently, on 3D space. Introducing a non-parametric representation to encode the temporal correlation among pairs of colorized depthmaps and 3D optical flow frames, a multi-stage Fully Convolutional Network (FCN) architecture is proposed to jointly learn reflector locations and their temporal dependency among sequential frames. The extracted reflector 2D locations are spatially mapped in 3D space, resulting in robust 3D optical data extraction. The subject's motion is efficiently captured by applying a template-based fitting technique on the extracted optical data. Two datasets have been created and made publicly available for evaluation purposes; one comprising multi-view depth and 3D optical flow annotated images (DMC2.5D), and a second, consisting of spatio-temporally aligned multi-view depth images along with skeleton, inertial and ground truth MoCap data (DMC3D). The FCN model outperforms its competitors on the DMC2.5D dataset using 2D Percentage of Correct Keypoints (PCK) metric, while the motion capture outcome is evaluated against RGB-D and inertial data fusion approaches on DMC3D, outperforming the next best method by 4.5% in total 3D PCK accuracy.

Georgios Albanis, Nikolaos Zioulis, Petros Drakoulis et al.

Pano3D is a new benchmark for depth estimation from spherical panoramas. It aims to assess performance across all depth estimation traits, the primary direct depth estimation performance targeting precision and accuracy, and also the secondary traits, boundary preservation, and smoothness. Moreover, Pano3D moves beyond typical intra-dataset evaluation to inter-dataset performance assessment. By disentangling the capacity to generalize to unseen data into different test splits, Pano3D represents a holistic benchmark for $360^o$ depth estimation. We use it as a basis for an extended analysis seeking to offer insights into classical choices for depth estimation. This results in a solid baseline for panoramic depth that follow-up works can build upon to steer future progress.

Hannes Fassold, Antonis Karakottas, Dorothea Tsatsou et al.

Spherical 360° video is a novel media format, rapidly becoming adopted in media production and consumption of immersive media. Due to its novelty, there is a lack of tools for producing highly engaging interactive 360° video for consumption on a multitude of platforms. In this work, we describe the work done so far in the Hyper360 project on tools for mixed 360° video and 3D content. Furthermore, the first pilots which have been produced with the Hyper360 tools and results of the audience assessment of the produced pilots are presented.

Konstantinos Konstantoudakis, David Breitgand, Alexandros Doumanoglou et al.

Immersive 3D media is an emerging type of media that captures, encodes and reconstructs the 3D appearance of people and objects, with applications in tele-presence, teleconference, entertainment, gaming and other fields. In this paper, we discuss a novel concept of live 3D immersive media streaming in a serverless setting. In particular, we present a novel network-centric adaptive streaming framework which deviates from a traditional client-based adaptive streaming used in 2D video. In our framework, the decisions for the production of the transcoding profiles are taken in a centralized manner, by considering consumer metrics vs provisioning costs and inferring an expected consumer quality of experience and behaviour based on them. In addition, we demonstrate that a naive application of the serverless paradigm might be sub optimal under some common immersive 3D media scenarios.

Nikolaos Zioulis, Federico Alvarez, Dimitrios Zarpalas et al.

It has been shown that global scene understanding tasks like layout estimation can benefit from wider field of views, and specifically spherical panoramas. While much progress has been made recently, all previous approaches rely on intermediate representations and postprocessing to produce Manhattan-aligned estimates. In this work we show how to estimate full room layouts in a single-shot, eliminating the need for postprocessing. Our work is the first to directly infer Manhattan-aligned outputs. To achieve this, our data-driven model exploits direct coordinate regression and is supervised end-to-end. As a result, we can explicitly add quasi-Manhattan constraints, which set the necessary conditions for a homography-based Manhattan alignment module. Finally, we introduce the geodesic heatmaps and loss and a boundary-aware center of mass calculation that facilitate higher quality keypoint estimation in the spherical domain. Our models and code are publicly available at https://vcl3d.github.io/SingleShotCuboids/.

Honglin Yuan, Remco C. Veltkamp, Georgios Albanis et al.

6D pose estimation is crucial for augmented reality, virtual reality, robotic manipulation and visual navigation. However, the problem is challenging due to the variety of objects in the real world. They have varying 3D shape and their appearances in captured images are affected by sensor noise, changing lighting conditions and occlusions between objects. Different pose estimation methods have different strengths and weaknesses, depending on feature representations and scene contents. At the same time, existing 3D datasets that are used for data-driven methods to estimate 6D poses have limited view angles and low resolution. To address these issues, we organize the Shape Retrieval Challenge benchmark on 6D pose estimation and create a physically accurate simulator that is able to generate photo-realistic color-and-depth image pairs with corresponding ground truth 6D poses. From captured color and depth images, we use this simulator to generate a 3D dataset which has 400 photo-realistic synthesized color-and-depth image pairs with various view angles for training, and another 100 captured and synthetic images for testing. Five research groups register in this track and two of them submitted their results. Data-driven methods are the current trend in 6D object pose estimation and our evaluation results show that approaches which fully exploit the color and geometric features are more robust for 6D pose estimation of reflective and texture-less objects and occlusion. This benchmark and comparative evaluation results have the potential to further enrich and boost the research of 6D object pose estimation and its applications.

Georgios Albanis, Nikolaos Zioulis, Anastasios Dimou et al.

In this work we consider UAVs as cooperative agents supporting human users in their operations. In this context, the 3D localisation of the UAV assistant is an important task that can facilitate the exchange of spatial information between the user and the UAV. To address this in a data-driven manner, we design a data synthesis pipeline to create a realistic multimodal dataset that includes both the exocentric user view, and the egocentric UAV view. We then exploit the joint availability of photorealistic and synthesized inputs to train a single-shot monocular pose estimation model. During training we leverage differentiable rendering to supplement a state-of-the-art direct regression objective with a novel smooth silhouette loss. Our results demonstrate its qualitative and quantitative performance gains over traditional silhouette objectives. Our data and code are available at https://vcl3d.github.io/DronePose

Vasileios Gkitsas, Nikolaos Zioulis, Federico Alvarez et al.

Estimating a scene's lighting is a very important task when compositing synthetic content within real environments, with applications in mixed reality and post-production. In this work we present a data-driven model that estimates an HDR lighting environment map from a single LDR monocular spherical panorama. In addition to being a challenging and ill-posed problem, the lighting estimation task also suffers from a lack of facile illumination ground truth data, a fact that hinders the applicability of data-driven methods. We approach this problem differently, exploiting the availability of surface geometry to employ image-based relighting as a data generator and supervision mechanism. This relies on a global Lambertian assumption that helps us overcome issues related to pre-baked lighting. We relight our training data and complement the model's supervision with a photometric loss, enabled by a differentiable image-based relighting technique. Finally, since we predict spherical spectral coefficients, we show that by imposing a distribution prior on the predicted coefficients, we can greatly boost performance. Code and models available at https://vcl3d.github.io/DeepPanoramaLighting.

Hannes Fassold, Antonis Karakottas, Dorothea Tsatsou et al.

360$^\circ$ video is a novel media format, rapidly becoming adopted in media production and consumption as part of todays ongoing virtual reality revolution. Due to its novelty, there is a lack of tools for producing highly engaging 360$^\circ$ video for consumption on a multitude of platforms. In this work, we describe the work done so far in the Hyper360 project on tools for 360$^\circ$ video. Furthermore, the first pilots which have been produced with the Hyper360 tools are presented.

Vladimiros Sterzentsenko, Alexandros Doumanoglou, Spyridon Thermos et al.

With the advent of consumer grade depth sensors, low-cost volumetric capture systems are easier to deploy. Their wider adoption though depends on their usability and by extension on the practicality of spatially aligning multiple sensors. Most existing alignment approaches employ visual patterns, e.g. checkerboards, or markers and require high user involvement and technical knowledge. More user-friendly and easier-to-use approaches rely on markerless methods that exploit geometric patterns of a physical structure. However, current SoA approaches are bounded by restrictions in the placement and the number of sensors. In this work, we improve markerless data-driven correspondence estimation to achieve more robust and flexible multi-sensor spatial alignment. In particular, we incorporate geometric constraints in an end-to-end manner into a typical segmentation based model and bridge the intermediate dense classification task with the targeted pose estimation one. This is accomplished by a soft, differentiable procrustes analysis that regularizes the segmentation and achieves higher extrinsic calibration performance in expanded sensor placement configurations, while being unrestricted by the number of sensors of the volumetric capture system. Our model is experimentally shown to achieve similar results with marker-based methods and outperform the markerless ones, while also being robust to the pose variations of the calibration structure. Code and pretrained models are available at https://vcl3d.github.io/StructureNet/.

Vasileios Gkitsas, Antonis Karakottas, Nikolaos Zioulis et al.

Machine learning is driven by data, yet while their availability is constantly increasing, training data require laborious, time consuming and error-prone labelling or ground truth acquisition, which in some cases is very difficult or even impossible. Recent works have resorted to synthetic data generation, but the inferior performance of models trained on synthetic data when applied to the real world, introduced the challenge of unsupervised domain adaptation. In this work we investigate an unsupervised domain adaptation technique that descends from another perspective, in order to avoid the complexity of adversarial training and cycle consistencies. We exploit the recent advances in photorealistic style transfer and take a fully data driven approach. While this concept is already implicitly formulated within the intricate objectives of domain adaptation GANs, we take an explicit approach and apply it directly as data pre-processing. The resulting technique is scalable, efficient and easy to implement, offers competitive performance to the complex state-of-the-art alternatives and can open up new pathways for domain adaptation.

Nikolaos Zioulis, Antonis Karakottas, Dimitrios Zarpalas et al.

Learning based approaches for depth perception are limited by the availability of clean training data. This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition procedures. Nonetheless, most research focuses on pinhole based monocular vision, with scarce works presenting results for omnidirectional input. In this work, we explore spherical view synthesis for learning monocular 360 depth in a self-supervised manner and demonstrate its feasibility. Under a purely geometrically derived formulation we present results for horizontal and vertical baselines, as well as for the trinocular case. Further, we show how to better exploit the expressiveness of traditional CNNs when applied to the equirectangular domain in an efficient manner. Finally, given the availability of ground truth depth data, our work is uniquely positioned to compare view synthesis against direct supervision in a consistent and fair manner. The results indicate that alternative research directions might be better suited to enable higher quality depth perception. Our data, models and code are publicly available at https://vcl3d.github.io/SphericalViewSynthesis/.

Antonis Karakottas, Nikolaos Zioulis, Stamatis Samaras et al.

Omnidirectional vision is becoming increasingly relevant as more efficient $360^o$ image acquisition is now possible. However, the lack of annotated $360^o$ datasets has hindered the application of deep learning techniques on spherical content. This is further exaggerated on tasks where ground truth acquisition is difficult, such as monocular surface estimation. While recent research approaches on the 2D domain overcome this challenge by relying on generating normals from depth cues using RGB-D sensors, this is very difficult to apply on the spherical domain. In this work, we address the unavailability of sufficient $360^o$ ground truth normal data, by leveraging existing 3D datasets and remodelling them via rendering. We present a dataset of $360^o$ images of indoor spaces with their corresponding ground truth surface normal, and train a deep convolutional neural network (CNN) on the task of monocular 360 surface estimation. We achieve this by minimizing a novel angular loss function defined on the hyper-sphere using simple quaternion algebra. We put an effort to appropriately compare with other state of the art methods trained on planar datasets and finally, present the practical applicability of our trained model on a spherical image re-lighting task using completely unseen data by qualitatively showing the promising generalization ability of our dataset and model. The dataset is available at: vcl3d.github.io/HyperSphereSurfaceRegression.

Vladimiros Sterzentsenko, Antonis Karakottas, Alexandros Papachristou et al.

Multi-view capture systems are complex systems to engineer. They require technical knowledge to install and intricate processes to setup related mainly to the sensors' spatial alignment (i.e. external calibration). However, with the ongoing developments in new production methods, we are now at a position where the production of high quality realistic 3D assets is possible even with commodity sensors. Nonetheless, the capturing systems developed with these methods are heavily intertwined with the methods themselves, relying on custom solutions and seldom - if not at all - publicly available. In light of this, we design, develop and publicly offer a multi-view capture system based on the latest RGB-D sensor technology. For our system, we develop a portable and easy-to-use external calibration method that greatly reduces the effort and knowledge required, as well as simplify the overall process.

Nikolaos Zioulis, Antonis Karakottas, Dimitrios Zarpalas et al.

Recent work on depth estimation up to now has only focused on projective images ignoring 360 content which is now increasingly and more easily produced. We show that monocular depth estimation models trained on traditional images produce sub-optimal results on omnidirectional images, showcasing the need for training directly on 360 datasets, which however, are hard to acquire. In this work, we circumvent the challenges associated with acquiring high quality 360 datasets with ground truth depth annotations, by re-using recently released large scale 3D datasets and re-purposing them to 360 via rendering. This dataset, which is considerably larger than similar projective datasets, is publicly offered to the community to enable future research in this direction. We use this dataset to learn in an end-to-end fashion the task of depth estimation from 360 images. We show promising results in our synthesized data as well as in unseen realistic images.

Dimitrios S. Alexiadis, Anargyros Chatzitofis, Nikolaos Zioulis et al.

The latest developments in 3D capturing, processing, and rendering provide means to unlock novel 3D application pathways. The main elements of an integrated platform, which target tele-immersion and future 3D applications, are described in this paper, addressing the tasks of real-time capturing, robust 3D human shape/appearance reconstruction, and skeleton-based motion tracking. More specifically, initially, the details of a multiple RGB-depth (RGB-D) capturing system are given, along with a novel sensors' calibration method. A robust, fast reconstruction method from multiple RGB-D streams is then proposed, based on an enhanced variation of the volumetric Fourier transform-based method, parallelized on the Graphics Processing Unit, and accompanied with an appropriate texture-mapping algorithm. On top of that, given the lack of relevant objective evaluation methods, a novel framework is proposed for the quantitative evaluation of real-time 3D reconstruction systems. Finally, a generic, multiple depth stream-based method for accurate real-time human skeleton tracking is proposed. Detailed experimental results with multi-Kinect2 data sets verify the validity of our arguments and the effectiveness of the proposed system and methodologies.