publications

2024

1. 

   FacadeNet: Conditional Facade Synthesis via Selective Editing

   Georgiou, Y.,  Loizou, M., Kelly, T., and Averkiou, M.

   In Proc. WACV, 2024

   Abs PDF Code Project Page

   We introduce FacadeNet, a deep learning approach for synthesizing building facade images from diverse viewpoints. Our method employs a conditional GAN, taking a single view of a facade along with the desired viewpoint information and generates an image of the facade from the distinct viewpoint. To precisely modify view-dependent elements like windows and doors while preserving the structure of view-independent components such as walls, we introduce a selective editing module. This module leverages image embeddings extracted from a pretrained vision transformer. Our experiments demonstrated state-of-the-art performance on building facade generation, surpassing alternative methods

2023

1. 

   Cross-Shape Attention for Part Segmentation of 3D Point Clouds

   Loizou, M., Garg, S., Petrov, D., Averkiou, M., and Kalogerakis, E.

   Computer Graphics Forum (Proc. SGP), 42(5), 2023

   Abs PDF Code Project Page

   We present a deep learning method that propagates point-wise feature representations across shapes within a collection for the purpose of 3D shape segmentation. We propose a cross-shape attention mechanism to enable interactions between a shape’s point-wise features and those of other shapes. The mechanism assesses both the degree of interaction between points and also mediates feature propagation across shapes, improving the accuracy and consistency of the resulting point-wise feature representations for shape segmentation. Our method also proposes a shape retrieval measure to select suitable shapes for cross-shape attention operations for each test shape. Our experiments demonstrate that our approach yields state-of-the-art results in the popular PartNet dataset.

2. 

   An artificial neural network framework for classifying the style of cypriot hybrid examples of built heritage in 3D

   Artopoulos, G., Maslioukova, M. I., Zavou, C.,  Loizou, M., Deligiorgi, M., and Averkiou, M.

   Journal of Cultural Heritage, 63(), 2023

   Abs PDF

   The article presents a workflow based on Deep Neural Networks (DNNs) and Support Vector Machine (SVM) for identifying architectural stylistic influences of segmented building parts of Cypriot historical architecture in 3D. The research contributes in the field of Digital Cultural Heritage (DCH) by applying Machine Learning (ML) and Deep Learning (DL) on recently published DCH data, with the aim to accelerate the segmentation and annotation process of Historic Building Information modelling (HBIM) that is currently based on time-consuming manual processes. The method presented works on reality captured data by 3D documentation techniques, precisely, Terrestrial Laser Scanning (TLS) or Photogrammetry. This workflow was developed to enable the operation of an online platform,11https://annfass-srv.cs.ucy.ac.cy. which also provides access to the building data presented here. Ultimately, the results of the presented method are accessible to scholars and students via this platform which provides multiple functionalities for researchers in the field to use.

2022

1. 

   PRIFIT: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation

   Sharma, G., Dash, B., RoyChowdhury, A., Gadelha, M.,  Loizou, M., Cao, L., Wang, R, Learned-Miller, E. G., Maji, S, and Kalogerakis, E.

   In Proc. SGP, 2022

   Abs PDF Code Project Page

   We present PriFit, a simple approach for label efficient learning of 3D shape segmentation networks. PriFit is based on a self-supervised task of decomposing the surface of a 3D shape into geometric primitives. It can be readily applied to existing network architectures for 3D shape segmentation, and improves their performance in the few-shot setting, as we demonstrate in the widely used ShapeNet and PartNet benchmarks. PriFit outperforms the prior state-of-the-art in this setting, suggesting that decomposability into primitives is a useful prior for learning representations predictive of semantic parts. We present a number of experiments varying the choice of geometric primitives and downstream tasks to demonstrate the effectiveness of the method.

2021

1. 

   BuildingNet: Learning to Label 3D Buildings

   Selvaraju, P., Nabail, M.,  Loizou, M., Maslioukova, M., Averkiou, M., Andreou, A., Chaudhuri, S., and Kalogerakis, E.

   In Proc. ICCV, 2021

   Abs PDF Code Project Page Video

   We introduce BuildingNet: (a) a large-scale dataset of 3D building models whose exteriors are consistently labeled, and (b) a graph neural network that labels building meshes by analyzing spatial and structural relations of their geometric primitives. To create our dataset, we used crowdsourcing combined with expert guidance, resulting in 513K annotated mesh primitives, grouped into 292K semantic part components across 2K building models. The dataset covers several building categories, such as houses, churches, skyscrapers, town halls, libraries, and castles. We include a benchmark for evaluating mesh and point cloud labeling. Buildings have more challenging structural complexity compared to objects in existing benchmarks (e.g., ShapeNet, PartNet), thus, we hope that our dataset can nurture the development of algorithms that are able to cope with such large-scale geometric data for both vision and graphics tasks e.g., 3D semantic segmentation, part-based generative models, correspondences, texturing, and analysis of point cloud data acquired from real-world buildings. Finally, we show that our mesh-based graph neural network significantly improves performance over several baselines for labeling 3D meshes. Our project page www.buildingnet.org includes our dataset and code.

2020

1. 

   Learning Part Boundaries from 3D Point Clouds

   Loizou, M., Averkiou, M., and Kalogerakis, E

   Computer Graphics Forum (Proc. SGP), 39(5), 2020

   Abs PDF Code Project Page Video

   We present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that separates two or more parts in a 3D shape. Our boundary detector is quite generic: it can be trained to localize boundaries of semantic parts or geometric primitives commonly used in 3D modeling. Our experiments demonstrate that our method can extract more accurate boundaries that are closer to ground-truth ones compared to alternatives. We also demonstrate an application of our network to fine-grained semantic shape segmentation, where we also show improvements in terms of part labeling performance.

2019

1. 

   Model-Based 3D Visual Tracking of Rigid Bodies using Distance Transform

   Loizou, M., and Kaimakis, P.

   In Proc. VISUAL, 2019

   Abs PDF Code

   The core idea of model-based 3D tracking is that of continuously estimating the pose parameters of a 3D object throughout a sequence of images, e.g., a video feed. Here, we present an edge-based method for achieving 3D object tracking, via Gauss-Newton optimization. We rely on natural features observations, like edges, for the detection of interest points and by using the 3D pose of the object in the previous frame, we correctly estimate its new 3D position and orientation, in real-time. There is also a C++ implementation of the visual tracking system, with the use of the OpenCV library, which can be found in our GitHub repository (https://github.com/marios2019/Visual Tracking).