Viktor Kocur

Charalambos Tzamos, Viktor Kocur, Yaqing Ding et al.

We study the challenging problem of estimating the relative pose of three calibrated cameras from four point correspondences. We propose novel efficient solutions to this problem that are based on the simple idea of using four correspondences to estimate an approximate geometry of the first two views. We model this geometry either as an affine or a fully perspective geometry estimated using one additional approximate correspondence. We generate such an approximate correspondence using a very simple and efficient strategy, where the new point is the mean point of three corresponding input points. The new solvers are efficient and easy to implement, since they are based on existing efficient minimal solvers, i.e., the 4-point affine fundamental matrix, the well-known 5-point relative pose solver, and the P3P solver. Extensive experiments on real data show that the proposed solvers, when properly coupled with local optimization, achieve state-of-the-art results, with the novel solver based on approximate mean-point correspondences being more robust and accurate than the affine-based solver.

Viktor Kocur, Daniel Kyselica, Zuzana Kukelova

The problem of self-calibration of two cameras from a given fundamental matrix is one of the basic problems in geometric computer vision. Under the assumption of known principal points and square pixels, the well-known Bougnoux formula offers a means to compute the two unknown focal lengths. However, in many practical situations, the formula yields inaccurate results due to commonly occurring singularities. Moreover, the estimates are sensitive to noise in the computed fundamental matrix and to the assumed positions of the principal points. In this paper, we therefore propose an efficient and robust iterative method to estimate the focal lengths along with the principal points of the cameras given a fundamental matrix and priors for the estimated camera parameters. In addition, we study a computationally efficient check of models generated within RANSAC that improves the accuracy of the estimated models while reducing the total computational time. Extensive experiments on real and synthetic data show that our iterative method brings significant improvements in terms of the accuracy of the estimated focal lengths over the Bougnoux formula and other state-of-the-art methods, even when relying on inaccurate priors.

Viktor Kocur, Sithu Aung, Gabrielle Flood et al.

Monocular depth estimation has improved significantly in recent years, driven by increasingly powerful models and large-scale training data. Predicted depth is increasingly used as an input signal for downstream tasks such as Structure-from-Motion (SfM), visual localization, and SLAM. However, monocular depth estimators (MDEs) are still primarily evaluated in terms of depth accuracy. Standard metrics aggregate errors globally and may not reflect the usefulness of depth for downstream geometric tasks. We therefore propose Depth2Pose, a framework for evaluating MDEs in the context of downstream tasks. By combining depth predictions with feature correspondences in depth-aware geometric solvers, we use relative camera pose estimation accuracy as a task-driven proxy for depth quality. Traditional benchmarks require dense ground truth in the form of per-pixel depth, which is expensive to obtain. In contrast, our formulation requires only camera poses, which can be estimated efficiently, e.g., using Structure-from-Motion pipelines. As a result, our framework can be applied to scenes where ground-truth depth is difficult to obtain, for example due to large scene scale or heavy occlusions (e.g., vegetated environments). Leveraging this, we introduce the D2P dataset, which contains challenging scenes outside the distribution of commonly used training data. We show that methods performing well under standard depth error metrics on existing benchmarks also perform well under our pose-based metric when evaluated on the same datasets, but do not necessarily generalize to our more challenging dataset. Finally, we provide a simple and extensible evaluation framework. The dataset and code are available at kocurvik.github.io/depth2pose.

Tomáš Kunzo, Viktor Kocur, Lukáš Gajdošech et al.

Teeth segmentation is an essential task in dental image analysis for accurate diagnosis and treatment planning. While supervised deep learning methods can be utilized for teeth segmentation, they often require extensive manual annotation of segmentation masks, which is time-consuming and costly. In this research, we propose a weakly supervised approach for teeth segmentation that reduces the need for manual annotation. Our method utilizes the output heatmaps and intermediate feature maps from a keypoint detection network to guide the segmentation process. We introduce the TriDental dataset, consisting of 3000 oral cavity images annotated with teeth keypoints, to train a teeth keypoint detection network. We combine feature maps from different layers of the keypoint detection network, enabling accurate teeth segmentation without explicit segmentation annotations. The detected keypoints are also used for further refinement of the segmentation masks. Experimental results on the TriDental dataset demonstrate the superiority of our approach in terms of accuracy and robustness compared to state-of-the-art segmentation methods. Our method offers a cost-effective and efficient solution for teeth segmentation in real-world dental applications, eliminating the need for extensive manual annotation efforts.

Martin Melicherčík, Lukáš Gajdošech, Viktor Kocur et al.

This paper focuses on increasing the resolution of depth maps obtained from 3D cameras using structured light technology. Two deep learning models FDSR and DKN are modified to work with high-resolution data, and data pre-processing techniques are implemented for stable training. The models are trained on our custom dataset of 1200 3D scans. The resulting high-resolution depth maps are evaluated using qualitative and quantitative metrics. The approach for depth map upsampling offers benefits such as reducing the processing time of a pipeline by first downsampling a high-resolution depth map, performing various processing steps at the lower resolution and upsampling the resulting depth map or increasing the resolution of a point cloud captured in lower resolution by a cheaper device. The experiments demonstrate that the FDSR model excels in terms of faster processing time, making it a suitable choice for applications where speed is crucial. On the other hand, the DKN model provides results with higher precision, making it more suitable for applications that prioritize accuracy.

Viktor Kocur, Charalambos Tzamos, Yaqing Ding et al.

Estimating the relative pose between two cameras is a fundamental step in many applications such as Structure-from-Motion. The common approach to relative pose estimation is to apply a minimal solver inside a RANSAC loop. Highly efficient solvers exist for pinhole cameras. Yet, (nearly) all cameras exhibit radial distortion. Not modeling radial distortion leads to (significantly) worse results. However, minimal radial distortion solvers are significantly more complex than pinhole solvers, both in terms of run-time and implementation efforts. This paper compares radial distortion solvers with two simple-to-implement approaches that do not use minimal radial distortion solvers: The first approach combines an efficient pinhole solver with sampled radial undistortion parameters, where the sampled parameters are used for undistortion prior to applying the pinhole solver. The second approach uses a state-of-the-art neural network to estimate the distortion parameters rather than sampling them from a set of potential values. Extensive experiments on multiple datasets, and different camera setups, show that complex minimal radial distortion solvers are not necessary in practice. We discuss under which conditions a simple sampling of radial undistortion parameters is preferable over calibrating cameras using a learning-based prior approach. Code and newly created benchmark for relative pose estimation under radial distortion are available at https://github.com/kocurvik/rdnet.

Yaqing Ding, Viktor Kocur, Zuzana Berger Haladová et al.

In this paper, we propose a novel approach for recovering focal lengths from three-view homographies. By examining the consistency of normal vectors between two homographies, we derive new explicit constraints between the focal lengths and homographies using an elimination technique. We demonstrate that three-view homographies provide two additional constraints, enabling the recovery of one or two focal lengths. We discuss four possible cases, including three cameras having an unknown equal focal length, three cameras having two different unknown focal lengths, three cameras where one focal length is known, and the other two cameras have equal or different unknown focal lengths. All the problems can be converted into solving polynomials in one or two unknowns, which can be efficiently solved using Sturm sequence or hidden variable technique. Evaluation using both synthetic and real data shows that the proposed solvers are both faster and more accurate than methods relying on existing two-view solvers. The code and data are available on https://github.com/kocurvik/hf

Zuzana Černeková, Zuzana Berger Haladová, Ján Špirka et al.

Outdoor advertising, such as roadside billboards, plays a significant role in marketing campaigns but can also be a distraction for drivers, potentially leading to accidents. In this study, we propose a pipeline for evaluating the significance of roadside billboards in videos captured from a driver's perspective. We have collected and annotated a new BillboardLamac dataset, comprising eight videos captured by drivers driving through a predefined path wearing eye-tracking devices. The dataset includes annotations of billboards, including 154 unique IDs and 155 thousand bounding boxes, as well as eye fixation data. We evaluate various object tracking methods in combination with a YOLOv8 detector to identify billboard advertisements with the best approach achieving 38.5 HOTA on BillboardLamac. Additionally, we train a random forest classifier to classify billboards into three classes based on the length of driver fixations achieving 75.8% test accuracy. An analysis of the trained classifier reveals that the duration of billboard visibility, its saliency, and size are the most influential features when assessing billboard significance.

Lukáš Hajdúch, Viktor Kocur

This paper presents a comprehensive pipeline for recognizing objects targeted by human pointing gestures using RGB images. As human-robot interaction moves toward more intuitive interfaces, the ability to identify targets of non-verbal communication becomes crucial. Our proposed system integrates several existing state-of-the-art methods, including object detection, body pose estimation, monocular depth estimation, and vision-language models. We evaluate the impact of 3D spatial information reconstructed from a single image and the utility of image captioning models in correcting classification errors. Experimental results on a custom dataset show that incorporating depth information significantly improves target identification, especially in complex scenes with overlapping objects. The modularity of the approach allows for deployment in environments where specialized depth sensors are unavailable.

Katarína Osvaldová, Lukáš Gajdošech, Viktor Kocur et al.

The goal of this paper is to assess the impact of noise in 3D camera-captured data by modeling the noise of the imaging process and applying it on synthetic training data. We compiled a dataset of specifically constructed scenes to obtain a noise model. We specifically model lateral noise, affecting the position of captured points in the image plane, and axial noise, affecting the position along the axis perpendicular to the image plane. The estimated models can be used to emulate noise in synthetic training data. The added benefit of adding artificial noise is evaluated in an experiment with rendered data for object segmentation. We train a series of neural networks with varying levels of noise in the data and measure their ability to generalize on real data. The results show that using too little or too much noise can hurt the networks' performance indicating that obtaining a model of noise from real scanners is beneficial for synthetic data generation.

Viktória Pravdová, Lukáš Gajdošech, Hassan Ali et al.

This paper investigates various methods of representing 3D rotations and their impact on the learning process of deep neural networks. We evaluated the performance of ResNet18 networks for 3D rotation estimation using several rotation representations and loss functions on both synthetic and real data. The real datasets contained 3D scans of industrial bins, while the synthetic datasets included views of a simple asymmetric object rendered under different rotations. On synthetic data, we also assessed the effects of different rotation distributions within the training and test sets, as well as the impact of the object's texture. In line with previous research, we found that networks using the continuous 5D and 6D representations performed better than the discontinuous ones.

Yaqing Ding, Viktor Kocur, Václav Vávra et al.

Recent advances in monocular depth estimation methods (MDE) and their improved accuracy open new possibilities for their applications. In this paper, we investigate how monocular depth estimates can be used for relative pose estimation. In particular, we are interested in answering the question whether using MDEs improves results over traditional point-based methods. We propose a novel framework for estimating the relative pose of two cameras from point correspondences with associated monocular depths. Since depth predictions are typically defined up to an unknown scale or even both unknown scale and shift parameters, our solvers jointly estimate the scale or both the scale and shift parameters along with the relative pose. We derive efficient solvers considering different types of depths for three camera configurations: (1) two calibrated cameras, (2) two cameras with an unknown shared focal length, and (3) two cameras with unknown different focal lengths. Our new solvers outperform state-of-the-art depth-aware solvers in terms of speed and accuracy. In extensive real experiments on multiple datasets and with various MDEs, we discuss which depth-aware solvers are preferable in which situation. The code will be made publicly available.

Matej Palider, Omar Eldardeer, Viktor Kocur

This paper evaluates the current gaze estimation methods within an HRI context of a shared workspace scenario. We introduce a new, annotated dataset collected with the NICO robotic platform. We evaluate four state-of-the-art gaze estimation models. The evaluation shows that the angular errors are close to those reported on general-purpose benchmarks. However, when expressed in terms of distance in the shared workspace the best median error is 16.48 cm quantifying the practical limitations of current methods. We conclude by discussing these limitations and offering recommendations on how to best integrate gaze estimation as a modality in HRI systems.

Andrej Macko, Lukáš Gajdošech, Viktor Kocur

This paper presents a computationally efficient method for vehicle speed estimation from traffic camera footage. Building upon previous work that utilizes 3D bounding boxes derived from 2D detections and vanishing point geometry, we introduce several improvements to enhance real-time performance. We evaluate our method in several variants on the BrnoCompSpeed dataset in terms of vehicle detection and speed estimation accuracy. Our extensive evaluation across various hardware platforms, including edge devices, demonstrates significant gains in frames per second (FPS) compared to the prior state-of-the-art, while maintaining comparable or improved speed estimation accuracy. We analyze the trade-off between accuracy and computational cost, showing that smaller models utilizing post-training quantization offer the best balance for real-world deployment. Our best performing model beats previous state-of-the-art in terms of median vehicle speed estimation error (0.58 km/h vs. 0.60 km/h), detection precision (91.02% vs 87.08%) and recall (91.14% vs. 83.32%) while also being 5.5 times faster.

Lukáš Gajdošech, Viktor Kocur, Martin Stuchlík et al.

An automated robotic system needs to be as robust as possible and fail-safe in general while having relatively high precision and repeatability. Although deep learning-based methods are becoming research standard on how to approach 3D scan and image processing tasks, the industry standard for processing this data is still analytically-based. Our paper claims that analytical methods are less robust and harder for testing, updating, and maintaining. This paper focuses on a specific task of 6D pose estimation of a bin in 3D scans. Therefore, we present a high-quality dataset composed of synthetic data and real scans captured by a structured-light scanner with precise annotations. Additionally, we propose two different methods for 6D bin pose estimation, an analytical method as the industrial standard and a baseline data-driven method. Both approaches are cross-evaluated, and our experiments show that augmenting the training on real scans with synthetic data improves our proposed data-driven neural model. This position paper is preliminary, as proposed methods are trained and evaluated on a relatively small initial dataset which we plan to extend in the future.

Viktor Kocur, Milan Ftáčnik

In this paper we propose a traffic surveillance camera calibration method based on detection of pairs of vanishing points associated with vehicles in the traffic surveillance footage. To detect the vanishing points we propose a CNN which outputs heatmaps in which the positions of vanishing points are represented using the diamond space parametrization which enables us to detect vanishing points from the whole infinite projective space. From the detected pairs of vanishing points for multiple vehicles in a scene we establish the scene geometry by estimating the focal length of the camera and the orientation of the road plane. We show that our method achieves competitive results on the BrnoCarPark dataset while having fewer requirements than the current state of the art approach.

Viktor Kocur, Milan Ftáčnik

Detection and tracking of vehicles captured by traffic surveillance cameras is a key component of intelligent transportation systems. We present an improved version of our algorithm for detection of 3D bounding boxes of vehicles, their tracking and subsequent speed estimation. Our algorithm utilizes the known geometry of vanishing points in the surveilled scene to construct a perspective transformation. The transformation enables an intuitive simplification of the problem of detecting 3D bounding boxes to detection of 2D bounding boxes with one additional parameter using a standard 2D object detector. Main contribution of this paper is an improved construction of the perspective transformation which is more robust and fully automatic and an extended experimental evaluation of speed estimation. We test our algorithm on the speed estimation task of the BrnoCompSpeed dataset. We evaluate our approach with different configurations to gauge the relationship between accuracy and computational costs and benefits of 3D bounding box detection over 2D detection. All of the tested configurations run in real-time and are fully automatic. Compared to other published state-of-the-art fully automatic results our algorithm reduces the mean absolute speed measurement error by 32% (1.10 km/h to 0.75 km/h) and the absolute median error by 40% (0.97 km/h to 0.58 km/h).