Charalambos Poullis

Yeshwanth Kumar Adimoolam, Bodhiswatta Chatterjee, Charalambos Poullis et al.

Recent advancements in deep learning and computer vision have led to widespread use of deep neural networks to extract building footprints from remote-sensing imagery. The success of such methods relies on the availability of large databases of high-resolution remote sensing images with high-quality annotations. The CrowdAI Mapping Challenge Dataset is one of these datasets that has been used extensively in recent years to train deep neural networks. This dataset consists of $ \sim\ $280k training images and $ \sim\ $60k testing images, with polygonal building annotations for all images. However, issues such as low-quality and incorrect annotations, extensive duplication of image samples, and data leakage significantly reduce the utility of deep neural networks trained on the dataset. Therefore, it is an imperative pre-condition to adopt a data validation pipeline that evaluates the quality of the dataset prior to its use. To this end, we propose a drop-in pipeline that employs perceptual hashing techniques for efficient de-duplication of the dataset and identification of instances of data leakage between training and testing splits. In our experiments, we demonstrate that nearly 250k($ \sim\ $90%) images in the training split were identical. Moreover, our analysis on the validation split demonstrates that roughly 56k of the 60k images also appear in the training split, resulting in a data leakage of 93%. The source code used for the analysis and de-duplication of the CrowdAI Mapping Challenge dataset is publicly available at https://github.com/yeshwanth95/CrowdAI_Hash_and_search .

Naghmeh Shafiee Roudbari, Zachary Patterson, Ursula Eicker et al.

In recent years, graph neural networks (GNNs) combined with variants of recurrent neural networks (RNNs) have reached state-of-the-art performance in spatiotemporal forecasting tasks. This is particularly the case for traffic forecasting, where GNN models use the graph structure of road networks to account for spatial correlation between links and nodes. Recent solutions are either based on complex graph operations or avoiding predefined graphs. This paper proposes a new sequence-to-sequence architecture to extract the spatiotemporal correlation at multiple levels of abstraction using GNN-RNN cells with sparse architecture to decrease training time compared to more complex designs. Encoding the same input sequence through multiple encoders, with an incremental increase in encoder layers, enables the network to learn general and detailed information through multilevel abstraction. We further present a new benchmark dataset of street-level segment traffic data from Montreal, Canada. Unlike highways, urban road segments are cyclic and characterized by complicated spatial dependencies. Experimental results on the METR-LA benchmark highway and our MSLTD street-level segment datasets demonstrate that our model improves performance by more than 7% for one-hour prediction compared to the baseline methods while reducing computing resource requirements by more than half compared to other competing methods.

Qiao Chen, Charalambos Poullis

Image-based 3D reconstruction is one of the most important tasks in Computer Vision with many solutions proposed over the last few decades. The objective is to extract metric information i.e. the geometry of scene objects directly from images. These can then be used in a wide range of applications such as film, games, virtual reality, etc. Recently, deep learning techniques have been proposed to tackle this problem. They rely on training on vast amounts of data to learn to associate features between images through deep convolutional neural networks and have been shown to outperform traditional procedural techniques. In this paper, we improve on the state-of-the-art two-view structure-from-motion(SfM) approach of [11] by incorporating 4D correlation volume for more accurate feature matching and reconstruction. Furthermore, we extend it to the general multi-view case and evaluate it on the complex benchmark dataset DTU [4]. Quantitative evaluations and comparisons with state-of-the-art multi-view 3D reconstruction methods demonstrate its superiority in terms of the accuracy of reconstructions.

Qiao Chen, Charalambos Poullis

Large displacement optical flow is an integral part of many computer vision tasks. Variational optical flow techniques based on a coarse-to-fine scheme interpolate sparse matches and locally optimize an energy model conditioned on colour, gradient and smoothness, making them sensitive to noise in the sparse matches, deformations, and arbitrarily large displacements. This paper addresses this problem and presents HybridFlow, a variational motion estimation framework for large displacements and deformations. A multi-scale hybrid matching approach is performed on the image pairs. Coarse-scale clusters formed by classifying pixels according to their feature descriptors are matched using the clusters' context descriptors. We apply a multi-scale graph matching on the finer-scale superpixels contained within each matched pair of coarse-scale clusters. Small clusters that cannot be further subdivided are matched using localized feature matching. Together, these initial matches form the flow, which is propagated by an edge-preserving interpolation and variational refinement. Our approach does not require training and is robust to substantial displacements and rigid and non-rigid transformations due to motion in the scene, making it ideal for large-scale imagery such as Wide-Area Motion Imagery (WAMI). More notably, HybridFlow works on directed graphs of arbitrary topology representing perceptual groups, which improves motion estimation in the presence of significant deformations. We demonstrate HybridFlow's superior performance to state-of-the-art variational techniques on two benchmark datasets and report comparable results with state-of-the-art deep-learning-based techniques.

Majid Pourmemar, Yashas Joshi, Charalambos Poullis

There are currently limited guidelines on designing user interfaces (UI) for immersive augmented reality (AR) applications. Designers must reflect on their experience designing UI for desktop and mobile applications and conjecture how a UI will influence AR users' performance. In this work, we introduce a predictive model for determining users' performance for a target UI without the subsequent involvement of participants in user studies. The model is trained on participants' responses to objective performance measures such as consumed endurance (CE) and pointing time (PT) using hierarchical drop-down menus. Large variability in the depth and context of the menus is ensured by randomly and dynamically creating the hierarchical drop-down menus and associated user tasks from words contained in the lexical database WordNet. Subjective performance bias is reduced by incorporating the users' non-verbal standard performance WAIS-IV during the model training. The semantic information of the menu is encoded using the Universal Sentence Encoder. We present the results of a user study that demonstrates that the proposed predictive model achieves high accuracy in predicting the CE on hierarchical menus of users with various cognitive abilities. To the best of our knowledge, this is the first work on predicting CE in designing UI for immersive AR applications.

Shima Shahfar, Charalambos Poullis

The Swapping Autoencoder achieved state-of-the-art performance in deep image manipulation and image-to-image translation. We improve this work by introducing a simple yet effective auxiliary module based on gradient reversal layers. The auxiliary module's loss forces the generator to learn to reconstruct an image with an all-zero texture code, encouraging better disentanglement between the structure and texture information. The proposed attribute-based transfer method enables refined control in style transfer while preserving structural information without using a semantic mask. To manipulate an image, we encode both the geometry of the objects and the general style of the input images into two latent codes with an additional constraint that enforces structure consistency. Moreover, due to the auxiliary loss, training time is significantly reduced. The superiority of the proposed model is demonstrated in complex domains such as satellite images where state-of-the-art are known to fail. Lastly, we show that our model improves the quality metrics for a wide range of datasets while achieving comparable results with multi-modal image generation techniques.

Ali Pourganjalikhan, Charalambos Poullis

Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames' predictions provides the network with richer cues for segmenting an object in the current frame. However, the size of the memory bank gradually increases with the length of the video, which slows down inference speed and makes it impractical to handle arbitrary length videos. This paper proposes an adaptive memory bank strategy for matching-based networks for semi-supervised video object segmentation (VOS) that can handle videos of arbitrary length by discarding obsolete features. Features are indexed based on their importance in the segmentation of the objects in previous frames. Based on the index, we discard unimportant features to accommodate new features. We present our experiments on DAVIS 2016, DAVIS 2017, and Youtube-VOS that demonstrate that our method outperforms state-of-the-art that employ first-and-latest strategy with fixed-sized memory banks and achieves comparable performance to the every-k strategy with increasing-sized memory banks. Furthermore, experiments show that our method increases inference speed by up to 80% over the every-k and 35% over first-and-latest strategies.

Amin Karimi, Charalambos Poullis

Few-shot semantic segmentation (FSS) aims to enable models to segment novel/unseen object classes using only a limited number of labeled examples. However, current FSS methods frequently struggle with generalization due to incomplete and biased feature representations, especially when support images do not capture the full appearance variability of the target class. To improve the FSS pipeline, we propose a novel framework that utilizes large language models (LLMs) to adapt general class semantic information to the query image. Furthermore, the framework employs dense pixel-wise matching to identify similarities between query and support images, resulting in enhanced FSS performance. Inspired by reasoning-based segmentation frameworks, our method, named DSV-LFS, introduces an additional token into the LLM vocabulary, allowing a multimodal LLM to generate a "semantic prompt" from class descriptions. In parallel, a dense matching module identifies visual similarities between the query and support images, generating a "visual prompt". These prompts are then jointly employed to guide the prompt-based decoder for accurate segmentation of the query image. Comprehensive experiments on the benchmark datasets Pascal-$5^{i}$ and COCO-$20^{i}$ demonstrate that our framework achieves state-of-the-art performance-by a significant margin-demonstrating superior generalization to novel classes and robustness across diverse scenarios. The source code is available at \href{https://github.com/aminpdik/DSV-LFS}{https://github.com/aminpdik/DSV-LFS}

Benyamin Mehmandar, Reza Talakoob, Charalambos Poullis

Currently, there are no learning-free or neural techniques for real-time recalibration of infrared multi-camera systems. In this paper, we address the challenge of real-time, highly-accurate calibration of multi-camera infrared systems, a critical task for time-sensitive applications. Unlike traditional calibration techniques that lack adaptability and struggle with on-the-fly recalibrations, we propose a neural network-based method capable of dynamic real-time calibration. The proposed method integrates a differentiable projection model that directly correlates 3D geometries with their 2D image projections and facilitates the direct optimization of both intrinsic and extrinsic camera parameters. Key to our approach is the dynamic camera pose synthesis with perturbations in camera parameters, emulating realistic operational challenges to enhance model robustness. We introduce two model variants: one designed for multi-camera systems with onboard processing of 2D points, utilizing the direct 2D projections of 3D fiducials, and another for image-based systems, employing color-coded projected points for implicitly establishing correspondence. Through rigorous experimentation, we demonstrate our method is more accurate than traditional calibration techniques with or without perturbations while also being real-time, marking a significant leap in the field of real-time multi-camera system calibration. The source code can be found at https://github.com/theICTlab/neural-recalibration

Milad Khanchi, Maria Amer, Charalambos Poullis

Current motion-based multiple object tracking (MOT) approaches rely heavily on Intersection-over-Union (IoU) for object association. Without using 3D features, they are ineffective in scenarios with occlusions or visually similar objects. To address this, our paper presents a novel depth-aware framework for MOT. We estimate depth using a zero-shot approach and incorporate it as an independent feature in the association process. Additionally, we introduce a Hierarchical Alignment Score that refines IoU by integrating both coarse bounding box overlap and fine-grained (pixel-level) alignment to improve association accuracy without requiring additional learnable parameters. To our knowledge, this is the first MOT framework to incorporate 3D features (monocular depth) as an independent decision matrix in the association step. Our framework achieves state-of-the-art results on challenging benchmarks without any training nor fine-tuning. The code is available at https://github.com/Milad-Khanchi/DepthMOT

Yeshwanth Kumar Adimoolam, Charalambos Poullis, Melinos Averkiou

Extraction of building footprint polygons from remotely sensed data is essential for several urban understanding tasks such as reconstruction, navigation, and mapping. Despite significant progress in the area, extracting accurate polygonal building footprints remains an open problem. In this paper, we introduce Pix2Poly, an attention-based end-to-end trainable and differentiable deep neural network capable of directly generating explicit high-quality building footprints in a ring graph format. Pix2Poly employs a generative encoder-decoder transformer to produce a sequence of graph vertex tokens whose connectivity information is learned by an optimal matching network. Compared to previous graph learning methods, ours is a truly end-to-end trainable approach that extracts high-quality building footprints and road networks without requiring complicated, computationally intensive raster loss functions and intricate training pipelines. Upon evaluating Pix2Poly on several complex and challenging datasets, we report that Pix2Poly outperforms state-of-the-art methods in several vector shape quality metrics while being an entirely explicit method. Our code is available at https://github.com/yeshwanth95/Pix2Poly.

Qing Gu, Kyriakos Herakleous, Charalambos Poullis

Recently, there has been an increase in the demand of virtual 3D objects representing real-life objects. A plethora of methods and systems have already been proposed for the acquisition of the geometry of real-life objects ranging from those which employ active sensor technology, passive sensor technology or a combination of various techniques. In this paper we present the development of a 3D scanning system which is based on the principle of structured-light, without having particular requirements for specialized equipment. We discuss the intrinsic details and inherent difficulties of structured-light scanning techniques and present our solutions. Finally, we introduce our open-source scanning software system "3DUNDERWORLD-SLS" which implements the proposed techniques both in CPU and GPU. We have performed extensive testing with a wide range of models and report the results. Furthermore, we present a comprehensive evaluation of the system and a comparison with a high-end commercial 3D scanner.

Harshitha Voleti, Charalambos Poullis

Prolonged mid-air interaction in virtual reality (VR) causes arm fatigue and discomfort, negatively affecting user experience. Incorporating ergonomic considerations into VR user interface (UI) design typically requires extensive human-in-the-loop evaluation. Although biomechanical models have been used to simulate human behavior in HCI tasks, their application as surrogate users for ergonomic VR UI design remains underexplored. We propose a hierarchical reinforcement learning framework that leverages biomechanical user models to evaluate and optimize VR interfaces for mid-air interaction. A motion agent is trained to perform button-press tasks in VR under sequential conditions, using realistic movement strategies and estimating muscle-level effort via a validated three-compartment control with recovery (3CC-r) fatigue model. The simulated fatigue output serves as feedback for a UI agent that optimizes UI element layout via reinforcement learning (RL) to minimize fatigue. We compare the RL-optimized layout against a manually-designed centered baseline and a Bayesian optimized baseline. Results show that fatigue trends from the biomechanical model align with human user data. Moreover, the RL-optimized layout using simulated fatigue feedback produced significantly lower perceived fatigue in a follow-up human study. We further demonstrate the framework's extensibility via a simulated case study on longer sequential tasks with non-uniform interaction frequencies. To our knowledge, this is the first work using simulated biomechanical muscle fatigue as a direct optimization signal for VR UI layout design. Our findings highlight the potential of biomechanical user models as effective surrogate tools for ergonomic VR interface design, enabling efficient early-stage iteration with less reliance on extensive human participation.

Naghmeh Shafiee Roudbari, Ursula Eicker, Charalambos Poullis et al.

Hydrometric forecasting is crucial for managing water resources, flood prediction, and environmental protection. Water stations are interconnected, and this connectivity influences the measurements at other stations. However, the dynamic and implicit nature of water flow paths makes it challenging to extract a priori knowledge of the connectivity structure. We hypothesize that terrain elevation significantly affects flow and connectivity. To incorporate this, we use LiDAR terrain elevation data encoded through a Vision Transformer (ViT). The ViT, which has demonstrated excellent performance in image classification by directly applying transformers to sequences of image patches, efficiently captures spatial features of terrain elevation. To account for both spatial and temporal features, we employ GRU blocks enhanced with graph convolution, a method widely used in the literature. We propose a hybrid graph learning structure that combines static and dynamic graph learning. A static graph, derived from transformer-encoded LiDAR data, captures terrain elevation relationships, while a dynamic graph adapts to temporal changes, improving the overall graph representation. We apply graph convolution in two layers through these static and dynamic graphs. Our method makes daily predictions up to 12 days ahead. Empirical results from multiple water stations in Quebec demonstrate that our method significantly reduces prediction error by an average of 10\% across all days, with greater improvements for longer forecasting horizons.

Damian Bowness, Charalambos Poullis

When viewing a 3D Gaussian Splatting (3DGS) model from camera positions significantly outside the training data distribution, substantial visual noise commonly occurs. These artifacts result from the lack of training data in these extrapolated regions, leading to uncertain density, color, and geometry predictions from the model. To address this issue, we propose a novel real-time render-aware filtering method. Our approach leverages sensitivity scores derived from intermediate gradients, explicitly targeting instabilities caused by anisotropic orientations rather than isotropic variance. This filtering method directly addresses the core issue of generative uncertainty, allowing 3D reconstruction systems to maintain high visual fidelity even when users freely navigate outside the original training viewpoints. Experimental evaluation demonstrates that our method substantially improves visual quality, realism, and consistency compared to existing Neural Radiance Field (NeRF)-based approaches such as BayesRays. Critically, our filter seamlessly integrates into existing 3DGS rendering pipelines in real-time, unlike methods that require extensive post-hoc retraining or fine-tuning. Code and results at https://damian-bowness.github.io/EV3DGS

Milad Khanchi, Maria Amer, Charalambos Poullis

Multi-object tracking (MOT) methods often rely on Intersection-over-Union (IoU) for association. However, this becomes unreliable when objects are similar or occluded. Also, computing IoU for segmentation masks is computationally expensive. In this work, we use segmentation masks to capture object shapes, but we do not compute segmentation IoU. Instead, we fuse depth and mask features and pass them through a compact encoder trained self-supervised. This encoder produces stable object representations, which we use as an additional similarity cue alongside bounding box IoU and re-identification features for matching. We obtain depth maps from a zero-shot depth estimator and object masks from a promptable visual segmentation model to obtain fine-grained spatial cues. Our MOT method is the first to use the self-supervised encoder to refine segmentation masks without computing masks IoU. MOT can be divided into joint detection-ReID (JDR) and tracking-by-detection (TBD) models. The latter are computationally more efficient. Experiments of our TBD method on challenging benchmarks with non-linear motion, occlusion, and crowded scenes, such as SportsMOT and DanceTrack, show that our method outperforms the TBD state-of-the-art on most metrics, while achieving competitive performance on simpler benchmarks with linear motion, such as MOT17.

Naghmeh Shafiee Roudbari, Charalambos Poullis, Zachary Patterson et al.

The hydrometric prediction of water quantity is useful for a variety of applications, including water management, flood forecasting, and flood control. However, the task is difficult due to the dynamic nature and limited data of water systems. Highly interconnected water systems can significantly affect hydrometric forecasting. Consequently, it is crucial to develop models that represent the relationships between other system components. In recent years, numerous hydrological applications have been studied, including streamflow prediction, flood forecasting, and water quality prediction. Existing methods are unable to model the influence of adjacent regions between pairs of variables. In this paper, we propose a spatiotemporal forecasting model that augments the hidden state in Graph Convolution Recurrent Neural Network (GCRN) encoder-decoder using an efficient version of the attention mechanism. The attention layer allows the decoder to access different parts of the input sequence selectively. Since water systems are interconnected and the connectivity information between the stations is implicit, the proposed model leverages a graph learning module to extract a sparse graph adjacency matrix adaptively based on the data. Spatiotemporal forecasting relies on historical data. In some regions, however, historical data may be limited or incomplete, making it difficult to accurately predict future water conditions. Further, we present a new benchmark dataset of water flow from a network of Canadian stations on rivers, streams, and lakes. Experimental results demonstrate that our proposed model TransGlow significantly outperforms baseline methods by a wide margin.

Alen Joy, Charalambos Poullis

This paper presents a process for estimating the spatially varying surface reflectance of complex scenes observed under natural illumination. In contrast to previous methods, our process is not limited to scenes viewed under controlled lighting conditions but can handle complex indoor and outdoor scenes viewed under arbitrary illumination conditions. An end-to-end process uses a model of the scene's geometry and several images capturing the scene's surfaces from arbitrary viewpoints and under various natural illumination conditions. We develop a differentiable path tracer that leverages least-square conformal mapping for handling multiple disjoint objects appearing in the scene. We follow a two-step optimization process and introduce a multi-view gradient consistency loss which results in up to 30-50% improvement in the image reconstruction loss and can further achieve better disentanglement of the diffuse and specular BRDFs compared to other state-of-the-art. We demonstrate the process in real-world indoor and outdoor scenes from images in the wild and show that we can produce realistic renders consistent with actual images using the estimated reflectance properties. Experiments show that our technique produces realistic results for arbitrary outdoor scenes with complex geometry. The source code is publicly available at: https://gitlab.com/alen.joy/multi-view-gradient-consistency-for-svbrdf-estimation-of-complex-scenes-under-natural-illumination

Farhan Rahman Wasee, Alen Joy, Charalambos Poullis

Estimating and modelling the appearance of an object under outdoor illumination conditions is a complex process. Although there have been several studies on illumination estimation and relighting, very few of them focus on estimating the reflectance properties of outdoor objects and scenes. This paper addresses this problem and proposes a complete framework to predict surface reflectance properties of outdoor scenes under unknown natural illumination. Uniquely, we recast the problem into its two constituent components involving the BRDF incoming light and outgoing view directions: (i) surface points' radiance captured in the images, and outgoing view directions are aggregated and encoded into reflectance maps, and (ii) a neural network trained on reflectance maps of renders of a unit sphere under arbitrary light directions infers a low-parameter reflection model representing the reflectance properties at each surface in the scene. Our model is based on a combination of phenomenological and physics-based scattering models and can relight the scenes from novel viewpoints. We present experiments that show that rendering with the predicted reflectance properties results in a visually similar appearance to using textures that cannot otherwise be disentangled from the reflectance properties.

Mohsen Parisay, Charalambos Poullis, Marta Kersten

One of the main challenges of gaze-based interactions is the ability to distinguish normal eye function from a deliberate interaction with the computer system, commonly referred to as 'Midas touch'. In this paper we propose, EyeTAP (Eye tracking point-and-select by Targeted Acoustic Pulse) a hands-free interaction method for point-and-select tasks. We evaluated the prototype in two separate user studies, each containing two experiments with 33 participants and found that EyeTAP is robust even in presence of ambient noise in the audio input signal with tolerance of up to 70 dB, results in a faster movement time, and faster task completion time, and has a lower cognitive workload than voice recognition. In addition, EyeTAP has a lower error rate than the dwell-time method in a ribbon-shaped experiment. These characteristics make it applicable for users for whom physical movements are restricted or not possible due to a disability. Furthermore, EyeTAP has no specific requirements in terms of user interface design and therefore it can be easily integrated into existing systems with minimal modifications. EyeTAP can be regarded as an acceptable alternative to address the Midas touch.

Bodhiswatta Chatterjee, Charalambos Poullis

In this paper we address three different aspects of semantic segmentation from remote sensor data using deep neural networks. Firstly, we focus on the semantic segmentation of buildings from remote sensor data and propose ICT-Net. The proposed network has been tested on the INRIA and AIRS benchmark datasets and is shown to outperform all other state of the art by more than 1.5% and 1.8% on the Jaccard index, respectively. Secondly, as the building classification is typically the first step of the reconstruction process, we investigate the relationship of the classification accuracy to the reconstruction accuracy. Finally, we present the simple yet compelling concept of latent learning and the implications it carries within the context of deep learning. We posit that a network trained on a primary task (i.e. building classification) is unintentionally learning about auxiliary tasks (e.g. the classification of road, tree, etc) which are complementary to the primary task. We extensively tested the proposed technique on the ISPRS benchmark dataset which contains multi-label ground truth, and report an average classification accuracy (F1 score) of 54.29% (SD=17.03) for roads, 10.15% (SD=2.54) for cars, 24.11% (SD=5.25) for trees, 42.74% (SD=6.62) for low vegetation, and 18.30% (SD=16.08) for clutter. The source code and supplemental material is publicly available at http://www.theICTlab.org/lp/2019ICT-Net/.

Yuanlie He, Sudhir Mudur, Charalambos Poullis

Object classification is one of the many holy grails in computer vision and as such has resulted in a very large number of algorithms being proposed already. Specifically in recent years there has been considerable progress in this area primarily due to the increased efficiency and accessibility of deep learning techniques. In fact, for single-label object classification [i.e. only one object present in the image] the state-of-the-art techniques employ deep neural networks and are reporting very close to human-like performance. There are specialized applications in which single-label object-level classification will not suffice; for example in cases where the image contains multiple intertwined objects of different labels. In this paper, we address the complex problem of multi-label pixelwise classification. We present our distinct solution based on a convolutional neural network (CNN) for performing multi-label pixelwise classification and its application to large-scale urban reconstruction. A supervised learning approach is followed for training a 13-layer CNN using both LiDAR and satellite images. An empirical study has been conducted to determine the hyperparameters which result in the optimal performance of the CNN. Scale invariance is introduced by training the network on five different scales of the input and labeled data. This results in six pixelwise classifications for each different scale. An SVM is then trained to map the six pixelwise classifications into a single-label. Lastly, we refine boundary pixel labels using graph-cuts for maximum a-posteriori (MAP) estimation with Markov Random Field (MRF) priors. The resulting pixelwise classification is then used to accurately extract and reconstruct the buildings in large-scale urban areas. The proposed approach has been extensively tested and the results are reported.