Pavel Zemčík

Aleksandr Algasov, Ekaterina Nepovinnykh, Fedor Zolotarev et al.

Existing individual re-identification methods often struggle with the deformable nature of animal fur or skin patterns which undergo geometric distortions due to body movement and posture changes. In this paper, we propose a geometry-aware texture mapping approach that unwarps pelage patterns, the unique markings found on an animal's skin or fur, into a canonical UV space, enabling more robust feature matching. Our method uses surface normal estimation to guide the unwrapping process while preserving the geometric consistency between the 3D surface and the 2D texture space. We focus on two challenging species: Saimaa ringed seals (Pusa hispida saimensis) and leopards (Panthera pardus). Both species have distinctive yet highly deformable fur patterns. By integrating our pattern-preserving UV mapping with existing re-identification techniques, we demonstrate improved accuracy across diverse poses and viewing angles. Our framework does not require ground truth UV annotations and can be trained in a self-supervised manner. Experiments on seal and leopard datasets show up to a 5.4% improvement in re-identification accuracy.

Bořek Reich, Matej Kunda, Fedor Zolotarev et al.

We propose a novel, good-quality, and less demanding method for detecting knots on the surface of wooden logs using multimodal data fusion. Knots are a primary factor affecting the quality of sawn timber, making their detection fundamental to any timber grading or cutting optimization system. While X-ray computed tomography provides accurate knot locations and internal structures, it is often too slow or expensive for practical use. An attractive alternative is to use fast and cost-effective log surface measurements, such as laser scanners or RGB cameras, to detect surface knots and estimate the internal structure of wood. However, due to the small size of knots and noise caused by factors, such as bark and other natural variations, detection accuracy often remains low when only one measurement modality is used. In this paper, we demonstrate that by using a data fusion pipeline consisting of separate streams for RGB and point cloud data, combined by a late fusion module, higher knot detection accuracy can be achieved compared to using either modality alone. We further propose a simple yet efficient sawing angle optimization method that utilizes surface knot detections and cross-correlation to minimize the amount of unwanted arris knots, demonstrating its benefits over randomized sawing angles.

Samuel Repka, Bořek Reich, Fedor Zolotarev et al.

We propose a novel Graph Neural Network-based method for segmentation based on data fusion of multimodal Scanning Electron Microscope (SEM) images. In most cases, Backscattered Electron (BSE) images obtained using SEM do not contain sufficient information for mineral segmentation. Therefore, imaging is often complemented with point-wise Energy-Dispersive X-ray Spectroscopy (EDS) spectral measurements that provide highly accurate information about the chemical composition but that are time-consuming to acquire. This motivates the use of sparse spectral data in conjunction with BSE images for mineral segmentation. The unstructured nature of the spectral data makes most traditional image fusion techniques unsuitable for BSE-EDS fusion. We propose using graph neural networks to fuse the two modalities and segment the mineral phases simultaneously. Our results demonstrate that providing EDS data for as few as 1% of BSE pixels produces accurate segmentation, enabling rapid analysis of mineral samples. The proposed data fusion pipeline is versatile and can be adapted to other domains that involve image data and point-wise measurements.

David Barina, Tomas Chlubna, Marek Solony et al.

Light field data records the amount of light at multiple points in space, captured e.g. by an array of cameras or by a light-field camera that uses microlenses. Since the storage and transmission requirements for such data are tremendous, compression techniques for light fields are gaining momentum in recent years. Although plenty of efficient compression formats do exist for still and moving images, only a little research on the impact of these methods on light field imagery is performed. In this paper, we evaluate the impact of state-of-the-art image and video compression methods on quality of images rendered from light field data. The methods include recent video compression standards, especially AV1 and XVC finalised in 2018. To fully exploit the potential of common image compression methods on four-dimensional light field imagery, we have extended these methods into three and four dimensions. In this paper, we show that the four-dimensional light field data can be compressed much more than independent still images while maintaining the same visual quality of a perceived picture. We gradually compare the compression performance of all image and video compression methods, and eventually answer the question, "What is the best compression method for light field data?".

David Barina, Pavel Najman, Petr Kleparnik et al.

The discrete wavelet transform can be found at the heart of many image-processing algorithms. Until now, the transform on general-purpose processors (CPUs) was mostly computed using a separable lifting scheme. As the lifting scheme consists of a small number of operations, it is preferred for processing using single-core CPUs. However, considering a parallel processing using multi-core processors, this scheme is inappropriate due to a large number of steps. On such architectures, the number of steps corresponds to the number of points that represent the exchange of data. Consequently, these points often form a performance bottleneck. Our approach appropriately rearranges calculations inside the transform, and thereby reduces the number of steps. In other words, we propose a new scheme that is friendly to parallel environments. When evaluating on multi-core CPUs, we consistently overcome the original lifting scheme. The evaluation was performed on 61-core Intel Xeon Phi and 8-core Intel Xeon processors.

David Barina, Michal Kula, Michal Matysek et al.

The two-dimensional discrete wavelet transform has a huge number of applications in image-processing techniques. Until now, several papers compared the performance of such transform on graphics processing units (GPUs). However, all of them only dealt with lifting and convolution computation schemes. In this paper, we show that corresponding horizontal and vertical lifting parts of the lifting scheme can be merged into non-separable lifting units, which halves the number of steps. We also discuss an optimization strategy leading to a reduction in the number of arithmetic operations. The schemes were assessed using the OpenCL and pixel shaders. The proposed non-separable lifting scheme outperforms the existing schemes in many cases, irrespective of its higher complexity.

David Barina, Michal Kula, Michal Matysek et al.

The 2-D discrete wavelet transform (DWT) can be found in the heart of many image-processing algorithms. Until recently, several studies have compared the performance of such transform on various shared-memory parallel architectures, especially on graphics processing units (GPUs). All these studies, however, considered only separable calculation schemes. We show that corresponding separable parts can be merged into non-separable units, which halves the number of steps. In addition, we introduce an optional optimization approach leading to a reduction in the number of arithmetic operations. The discussed schemes were adapted on the OpenCL framework and pixel shaders, and then evaluated using GPUs of two biggest vendors. We demonstrate the performance of the proposed non-separable methods by comparison with existing separable schemes. The non-separable schemes outperform their separable counterparts on numerous setups, especially considering the pixel shaders.

Jakub Sochor, Roman Juránek, Jakub Špaňhel et al.

In this paper, we focus on traffic camera calibration and a visual speed measurement from a single monocular camera, which is an important task of visual traffic surveillance. Existing methods addressing this problem are difficult to compare due to a lack of a common data set with reliable ground truth. Therefore, it is not clear how the methods compare in various aspects and what factors are affecting their performance. We captured a new data set of 18 full-HD videos, each around 1 hr long, captured at six different locations. Vehicles in the videos (20865 instances in total) are annotated with the precise speed measurements from optical gates using LiDAR and verified with several reference GPS tracks. We made the data set available for download and it contains the videos and metadata (calibration, lengths of features in image, annotations, and so on) for future comparison and evaluation. Camera calibration is the most crucial part of the speed measurement; therefore, we provide a brief overview of the methods and analyze a recently published method for fully automatic camera calibration and vehicle speed measurement and report the results on this data set in detail.

Bronislav Přibyl, Pavel Zemčík, Martin Čadík

This work is concerned with camera pose estimation from correspondences of 3D/2D lines, i. e. with the Perspective-n-Line (PnL) problem. We focus on large line sets, which can be efficiently solved by methods using linear formulation of PnL. We propose a novel method "DLT-Combined-Lines" based on the Direct Linear Transformation (DLT) algorithm, which benefits from a new combination of two existing DLT methods for pose estimation. The method represents 2D structure by lines, and 3D structure by both points and lines. The redundant 3D information reduces the minimum required line correspondences to 5. A cornerstone of the method is a combined projection matri xestimated by the DLT algorithm. It contains multiple estimates of camera rotation and translation, which can be recovered after enforcing constraints of the matrix. Multiplicity of the estimates is exploited to improve the accuracy of the proposed method. For large line sets (10 and more), the method is comparable to the state-of-theart in accuracy of orientation estimation. It achieves state-of-the-art accuracy in estimation of camera position and it yields the smallest reprojection error under strong image noise. The method achieves top-3 results on real world data. The proposed method is also highly computationally effective, estimating the pose of 1000 lines in 12 ms on a desktop computer.

David Barina, Michal Kula, Pavel Zemcik

In this paper, we introduce several new schemes for calculation of discrete wavelet transforms of images. These schemes reduce the number of steps and, as a consequence, allow to reduce the number of synchronizations on parallel architectures. As an additional useful property, the proposed schemes can reduce also the number of arithmetic operations. The schemes are primarily demonstrated on CDF 5/3 and CDF 9/7 wavelets employed in JPEG 2000 image compression standard. However, the presented method is general, and it can be applied on any wavelet transform. As a result, our scheme requires only two memory barriers for 2-D CDF 5/3 transform compared to four barriers in the original separable form or three barriers in the non-separable scheme recently published. Our reasoning is supported by exhaustive experiments on high-end graphics cards.

Pavel Svoboda, Michal Hradis, David Barina et al.

This paper shows that it is possible to train large and deep convolutional neural networks (CNN) for JPEG compression artifacts reduction, and that such networks can provide significantly better reconstruction quality compared to previously used smaller networks as well as to any other state-of-the-art methods. We were able to train networks with 8 layers in a single step and in relatively short time by combining residual learning, skip architecture, and symmetric weight initialization. We provide further insights into convolution networks for JPEG artifact reduction by evaluating three different objectives, generalization with respect to training dataset size, and generalization with respect to JPEG quality level.

Martin Kolář, Michal Hradiš, Pavel Zemčík

This report presents our submission to the MS COCO Captioning Challenge 2015. The method uses Convolutional Neural Network activations as an embedding to find semantically similar images. From these images, the most typical caption is selected based on unigram frequencies. Although the method received low scores with automated evaluation metrics and in human assessed average correctness, it is competitive in the ratio of captions which pass the Turing test and which are assessed as better or equal to human captions.