2D Image Sequences Research Articles

A Graph Theory Study of Resting-State Functional MRI Connectivity in Children With Carbon Monoxide Poisoning.

The effect of carbon monoxide (CO) poisoning on the topology of brain functional networks is unclear, especially in children whose brains are still developing. To investigate the topological alterations of the whole-brain functional connectome in children with CO poisoning and characterize its relationship with disease severity. Cross-sectional and prospective study. A total of 26 patients with CO poisoning and 26 healthy controls. A 3.0 T MRI system/echo planar imaging (EPI) and 3D brain volume imaging (BRAVO) sequences. We used the network-based statistics (NBS) method to explore between-group differences in functional connectivity strength and a graph-theoretical-based analytic method to explore the topology of brain networks. Student's t-test, chi-square test, NBS, Pearson correlation coefficient, and false discovery rate correction. The statistical significance threshold was set at P < 0.05. The case group's brain functional network topology was impaired in comparison to the control group (reduced global efficiency and small-worldness, increased characteristic path length). According to node and edge analyses, the case group showed topologically damaged regions in the frontal lobe and basal ganglia, as well as neuronal circuits with weaker connections. Also, there was a significant correlation between the patients' coma time and the degree (r = -0.4564), efficiency (r = -0.4625), and characteristic path length (r = 0.4383) of the nodes in the left orbital inferior frontal gyrus. Carbon monoxide hemoglobin content (COHb) concentration and right rolandic operculum node characteristic path length (r = -0.3894) were significantly correlated. The node efficiency and node degree of the right middle frontal gyrus (r = 0.4447 and 0.4539) and right pallidum (r = 0.4136 and 0.4501) significantly correlated with the MMSE score. The brain network topology of CO poisoned children is damaged, which is manifested by reduced network integration and may lead to a series of clinical symptoms in patients. 2. Stage 2.

1.5-T MR relaxometry in quantifying splenic and pancreatic iron: retrospective comparison of a commercial 3D-Dixon sequence and an established 2D multi-gradient echo sequence

ObjectivesTo compare the quantitative measurement of splenic and pancreatic iron content using a commercial 3D-Dixon sequence (qDixon) versus an established fat-saturated R2* relaxometry method (ME-GRE).MethodsWe analyzed splenic and pancreatic iron levels in 143 MR examinations (1.5 T) using the qDixon and a ME-GRE sequence (108 patients: 65 males, 43 females, mean age 61.31 years). Splenic and pancreatic R2* values were compared between both methods using Bland–Altman plots, concordance correlation coefficients (CCC), and linear regression analyses. Iron overload (R2* > 50 1/s) was defined for both organs and compared using contingency tables, overall agreement, and Gwet’s AC1 coefficient.ResultsOf all analyzable examinations, the median splenic R2* using the qDixon sequence was 25.75 1/s (range: 5.6–433) and for the ME-GRE sequence 35.35 1/s (range: 10.9–400.8) respectively. Concerning the pancreas, a median R2* of 29.93 1/s (range: 14–111.45) for the qDixon and 31.25 1/s (range: 14–97) for the ME-GRE sequence was found. Bland–Altman analysis showed a mean R2* difference of 2.12 1/s with a CCC of 0.934 for the spleen and of 0.29 1/s with a CCC of 0.714 for the pancreas. Linear regression for the spleen/pancreas resulted in a correlation coefficient of 0.94 (p < 0.001)/0.725 (p < 0.001). Concerning iron overload, the proportion of overall agreement between the two methods was 91.43% for the spleen and 93.18% for the pancreas.ConclusionsOur data show good concordance between R2* values obtained with a commercial qDixon sequence and a validated ME-GRE relaxometry method. The 3D-qDixon sequence, originally intended for liver assessment, seems to be a reliable tool for non-invasive evaluation of iron content also in the spleen and the pancreas.Key Points• A 3D chemical shift imaging sequence and 2D multi-gradient echo sequence show good conformity quantifying splenic and pancreatic R2* values.• The 3D chemical shift imaging sequence allows a reliable analysis also of splenic and pancreatic iron status.• In addition to the liver, the analysis of the spleen and pancreas is often helpful for further differential diagnostic clarification and patient guidance regarding the iron status.

Monocular Quasi-Dense 3D Object Tracking.

A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform. The object association leverages quasi-dense similarity learning to identify objects in various poses and viewpoints with appearance cues only. After initial 2D association, we further utilize 3D bounding boxes depth-ordering heuristics for robust instance association and motion-based 3D trajectory prediction for re-identification of occluded vehicles. In the end, an LSTM-based object velocity learning module aggregates the long-term trajectory information for more accurate motion extrapolation. Experiments on our proposed simulation data and real-world benchmarks, including KITTI, nuScenes, and Waymo datasets, show that our tracking framework offers robust object association and tracking on urban-driving scenarios. On the Waymo Open benchmark, we establish the first camera-only baseline in the 3D tracking and 3D detection challenges. Our quasi-dense 3D tracking pipeline achieves impressive improvements on the nuScenes 3D tracking benchmark with near five times tracking accuracy of the best vision-only submission among all published methods.

Visual Three-Dimensional Reconstruction Based on Spatiotemporal Analysis Method

To accurately reconstruct the three-dimensional (3D) surface of dynamic objects, we proposed a wrapped phase extraction method for spatiotemporal analysis based on 3D wavelet transform (WT). Our proposed method uses a 2D spatial fringe image combined with the time dimension and forms a 3D image sequence. The encoded fringe image sequence’s wrapped phase information was extracted by 3D WT and complex Morlet wavelet, and we improved the wrapped phase extraction’s accuracy by using the characteristics of spatiotemporal analysis and a multi-scale analysis of 3D WT, then we reconstructed the measured object by wrapped phase unwrapping and phase height transformation. Our simulation experiment results show that our proposed method can further filter the noise in the time dimension, and its accuracy is better than that of the one- (1D) and two-dimensional (2D) WT wrapped phase extraction method and the 3D Fourier transform wrapped phase extraction method because the reconstructed spherical crown’s RMSE value does not exceed 0.25 and the PVE value is less than 0.95. Our results show that the proposed method can be applied to the dynamic 3D reconstruction of a real human thoracic and abdominal surface, which fluctuates slowly with respiration movement, further verifying its effectiveness.

Direct observation of C3S particle dissolution using fast nano X-ray computed tomography

This paper uses a sequence of 3D images at a 50 nm pixel size to study the dissolution behavior of tricalcium silicate (C3S) particles with a water to solids ratio of 1.10 from 18 min to 7 h of hydration. 550 particles with dimensions ranging from 0.41 μm to 12 μm were directly observed. The results suggest that C3S particles have different dissolution rates with time; however, the dissolution rate seems to correlate well with the particle surface area and is independent of the particle size. These findings provide insights into the behavior of C3S materials and are an important step in understanding and modeling the dissolution of these materials.

X‐ray Tomography and Tomoscopy on Metals: A Review

X‐ray tomography is a versatile tool in materials research and engineering since it allows for a non‐destructive and three‐dimensional mapping of the constituents of a heterogeneous material as long as they differ in their interactions with X‐rays. Recent developments of the technique have brought down the time needed for the acquisition of a single tomogram by many orders of magnitude compared to what was needed 25 years ago. Nowadays, up to 1000 full tomograms can be recorded in a second, which enables real‐time studies of changes in samples caused by reactions or by applied processing operations. The term tomoscopy has been coined for such sequences of 3D images. We review the application of X‐ray tomography and tomoscopy on metals and describe each step required and the associated challenges. A selection of representative investigations is presented with a focus on time‐resolved phenomena in metals and alloys ranging from mechanical deformation, solidification to metals processing processes such as welding and additive manufacturing. Finally likely future developments are discussed.

Depth Estimation using DNN Architecture and Vision-Based Transformers

Depth Estimation is the process of estimating the depth of objects with a 2D image as an input. The importance of Depth Estimation is that it provides some critical information about the 3D structure of a scene given a sequence of 2D images. This is helpful in various applications like robotics, virtual reality, autonomous driving, medical imaging, and so on and so forth. Our main objective here is to make the environment more perceivable by autonomous vehicles. Unlike the traditional approaches which try to extract depth from the input image, we apply instance segmentation to the image and then use the segmented image as an input to the depth map generator. In this paper, we use a fully connected neural network with dense prediction transformers. As mentioned above, the image after instance segmentation is given as an input for the transformers. The Transformer is the backbone for producing high-resolution images. Our experimentation results have shown many improvements related to the details and sharpness of the image as compared to the traditional depth estimation techniques. The architecture is applied and tested on the KITTI data set.

Multifocus Image Reconstruction and Fusion for 3-D Flow Visualization Using an Optimized Four-Plane ECT Sensor

3D image reconstruction of permittivity distribution is very challenging for electrical capacitance tomography (ECT) because of the limited number of capacitance measurements and the non-uniformly distributed sensitivity, especially for axial distribution. In this paper, a 3D image reconstruction method based on fuzzy adaptive Kalman filter (FAKaF) and multi-focus image fusion is used to improve the 3D image quality. A four-plane ECT sensor is constructed and optimized based on the conformal transformation method, whose sensitivity in the imaging volume is more uniform in the axial direction. Then a FAKaF is established to obtain a series of initial reconstructed images with higher image quality in the central region, which can be seen as a sequence of multi-focus 3D images. Finally, an image registration and fusion method based on cross correlation and spatial frequency is used to extract and fuse the high-quality parts of each image in the sequence to further improve the quality of the reconstructed images. Simulations and experiments were carried out to evaluate the performance of the proposed method. The results show that compared with the widely-used methods, initial images reconstructed using the proposed FAKaF-based method possess higher image quality. Through image fusion, higher correlation coefficients between reference distributions and fused images can be obtained, proving the effectiveness of the proposed method.

Validation of a drift-corrected 3D MR temperature imaging sequence for breast MR-guided focused ultrasound treatments

Real-time temperature monitoring is critical to the success of thermally ablative therapies. This work validates a 3D thermometry sequence with k-space field drift correction designed for use in magnetic resonance-guided focused ultrasound treatments for breast cancer. Fiberoptic probes were embedded in tissue-mimicking phantoms, and temperature change measurements from the probes were compared with the magnetic resonance temperature imaging measurements following heating with focused ultrasound. Precision and accuracy of measurements were also evaluated in free-breathing healthy volunteers (N = 3) under a non-heating condition.MR temperature measurements agreed closely with those of fiberoptic probes, with a 95% confidence interval of measurement difference from −2.0 °C to 1.4 °C. Field drift-corrected measurements in vivo had a precision of 1.1 ± 0.7 °C and were accurate within 1.3 ± 0.9 °C across the three volunteers. The field drift correction method improved precision and accuracy by an average of 46 and 42%, respectively, when compared to the uncorrected data. This temperature imaging sequence can provide accurate measurements of temperature change in aqueous tissues in the breast and support the use of this sequence in clinical investigations of focused ultrasound treatments for breast cancer.

Scene-relative object motion biases depth percepts

An important function of the visual system is to represent 3D scene structure from a sequence of 2D images projected onto the retinae. During observer translation, the relative image motion of stationary objects at different distances (motion parallax) provides potent depth information. However, if an object moves relative to the scene, this complicates the computation of depth from motion parallax since there will be an additional component of image motion related to scene-relative object motion. To correctly compute depth from motion parallax, only the component of image motion caused by self-motion should be used by the brain. Previous experimental and theoretical work on perception of depth from motion parallax has assumed that objects are stationary in the world. Thus, it is unknown whether perceived depth based on motion parallax is biased by object motion relative to the scene. Naïve human subjects viewed a virtual 3D scene consisting of a ground plane and stationary background objects, while lateral self-motion was simulated by optic flow. A target object could be either stationary or moving laterally at different velocities, and subjects were asked to judge the depth of the object relative to the plane of fixation. Subjects showed a far bias when object and observer moved in the same direction, and a near bias when object and observer moved in opposite directions. This pattern of biases is expected if subjects confound image motion due to self-motion with that due to scene-relative object motion. These biases were large when the object was viewed monocularly, and were greatly reduced, but not eliminated, when binocular disparity cues were provided. Our findings establish that scene-relative object motion can confound perceptual judgements of depth during self-motion.

Combining sodium MRI, proton MR spectroscopic imaging, and intracerebral EEG in epilepsy.

Whole brain ionic and metabolic imaging has potential as a powerful tool for the characterization of brain diseases. We combined sodium MRI (23 Na MRI) and 1 H-MR Spectroscopic Imaging (1 H-MRSI), assessing changes within epileptogenic networks in comparison with electrophysiologically normal networks as defined by stereotactic EEG (SEEG) recordings analysis. We applied a multi-echo density adapted 3D projection reconstruction pulse sequence at 7T (23 Na-MRI) and a 3D echo-planar spectroscopic imaging sequence at 3T (1 H-MRSI) in 19 patients suffering from drug-resistant focal epilepsy who underwent presurgical SEEG. We investigated 23 Na MRI parameters including total sodium concentration (TSC) and the sodium signal fraction associated with the short component of T2 * decay (f), alongside the level of metabolites N-acetyl aspartate (NAA), choline compounds (Cho), and total creatine (tCr). All measures were extracted from spherical regions of interest (ROIs) centered between two adjacent SEEG electrode contacts and z-scored against the same ROI in controls. Group comparison showed a significant increase in f only in the epileptogenic zone (EZ) compared to controls and compared to patients' propagation zone (PZ) and non-involved zone (NIZ). TSC was significantly increased in all patients' regions compared to controls. Conversely, NAA levels were significantly lower in patients compared to controls, and lower in the EZ compared to PZ and NIZ. Multiple regression analyzing the relationship between sodium and metabolites levels revealed significant relations in PZ and in NIZ but not in EZ. Our results are in agreement with the energetic failure hypothesis in epileptic regions associated with widespread tissue reorganization.

Using temporal and structural data to reconstruct 3D cerebral vasculature from a pair of 2D digital subtraction angiography sequences.

The purpose of this work is to present a new method for reconstructing patient-specific three-dimensional (3D) vasculature of the brain from a pair of digital subtraction angiography (DSA) image sequences from different viewpoints, e.g., from bi-plane angiography. Our long-term goal is to provide high resolution visualization of 3D vasculature with dynamic flow of contrast agent from limited data that is readily available during surgical procedures. The proposed method is the second of a three-stage process composed of 1) augmenting vessel segmentation with vessel radii and timing of the arrival of a bolus of contrast agent, 2) reconstructing a volumetric representation of the augmented vessel data from the augmented 2D segmentations, and 3) generating a 3D model of vessels and flow of contrast agent from the volumetric reconstruction. Unlike previous methods, which are either limited to relatively simple vessel structures or rely on multiple views and/or prior models of the vasculature, our method requires only a single pair of 2D DSA sequences taken from different view directions. We developed a new mathematical algorithm that augments vessel centerlines with vessel radii and bolus arrival times derived directly from the 2D DSA sequences to constrain the 3D reconstruction. We validated this method on digital phantoms derived from clinical data and from fractal models of branching tree structures. In standard reconstruction methods, reconstruction by projection of two views into 3D space results in 'ghosting' artifacts, i.e., false 3D structure that occurs where vessels or vessel segments overlap in the 2D images. For the complex vascular of the brain, this ghosting is severe and is a major hurdle for methods that attempt to generate 3D structure from 2D images. We show that our approach reduces ghosting by up to 99% in digital phantoms derived from clinical data. Our dramatic reduction in ghosting artifacts in 3D reconstructions from a pair of 2D image sequences is an important step towards generating high resolution 3D vasculature with dynamic flow information from a single DSA sequence acquired using bi-plane angiography.

Magnetization Transfer BOOST Noncontrast Angiography Improves Pulmonary Vein Imaging in Adults With Congenital Heart Disease.

Cardiac MRI plays an important role in the diagnosis and follow-up of patients with congenital heart disease (CHD). Gadolinium-based contrast agents are often needed to overcome flow-related and off-resonance artifacts that can impair the quality of conventional noncontrast 3D imaging. As serial imaging is often required in CHD, the development of robust noncontrast 3D MRI techniques is desirable. To assess the clinical utility of noncontrast enhanced magnetization transfer and inversion recovery prepared 3D free-breathing sequence (MTC-BOOST) compared to conventional 3D whole heart imaging in patients with CHD. Prospective, image quality. A total of 27 adult patients (44% female, mean age 30.9 ± 14.8 years) with CHD. A 1.5 T; free-breathing 3D MTC-BOOST sequence. MTC-BOOST was compared to diaphragmatic navigator-gated, noncontrast T2 prepared 3D whole-heart imaging sequence (T2prep-3DWH) for comparison of vessel dimensions, lumen-to-myocardium contrast ratio (CR), and image quality (vessel wall sharpness and presence and type of artifacts) assessed by two experienced cardiologists on a 5-point scale. Mann-Whitney test, paired Wilcoxon signed-rank test, Bland-Altman plots. P < 0.05 was considered statistically significant. MTC-BOOST significantly improved image quality and CR of the right-sided pulmonary veins (PV): (CR: right upper PV 1.06 ± 0.50 vs. 0.58 ± 0.74; right lower PV 1.32 ± 0.38 vs. 0.81 ± 0.73) compared to conventional T2prep-3DWH imaging where the PVs were not visualized in some cases due to off-resonance effects. MTC-BOOST demonstrated resistance to degradation of luminal signal (assessed by CR) secondary to accelerated or turbulent flow conditions. T2prep-3DWH had higher image quality scores than MTC-BOOST for the aorta and coronary arteries; however, great vessel dimensions derived from MTC-BOOST showed excellent agreement with standard T2prep-3DWH imaging. MTC-BOOST allows for improved contrast-free imaging of pulmonary veins and regions characterized by accelerated or turbulent blood flow compared to standard T2prep-3DWH imaging, with excellent agreement of great vessel dimensions. 1 TECHNICAL EFFICACY: Stage 2.

High-throughput widefield fluorescence imaging of 3D samples using deep learning for 2D projection image restoration.

Fluorescence microscopy is a core method for visualizing and quantifying the spatial and temporal dynamics of complex biological processes. While many fluorescent microscopy techniques exist, due to its cost-effectiveness and accessibility, widefield fluorescent imaging remains one of the most widely used. To accomplish imaging of 3D samples, conventional widefield fluorescence imaging entails acquiring a sequence of 2D images spaced along the z-dimension, typically called a z-stack. Oftentimes, the first step in an analysis pipeline is to project that 3D volume into a single 2D image because 3D image data can be cumbersome to manage and challenging to analyze and interpret. Furthermore, z-stack acquisition is often time-consuming, which consequently may induce photodamage to the biological sample; these are major barriers for workflows that require high-throughput, such as drug screening. As an alternative to z-stacks, axial sweep acquisition schemes have been proposed to circumvent these drawbacks and offer potential of 100-fold faster image acquisition for 3D-samples compared to z-stack acquisition. Unfortunately, these acquisition techniques generate low-quality 2D z-projected images that require restoration with unwieldy, computationally heavy algorithms before the images can be interrogated. We propose a novel workflow to combine axial z-sweep acquisition with deep learning-based image restoration, ultimately enabling high-throughput and high-quality imaging of complex 3D-samples using 2D projection images. To demonstrate the capabilities of our proposed workflow, we apply it to live-cell imaging of large 3D tumor spheroid cultures and find we can produce high-fidelity images appropriate for quantitative analysis. Therefore, we conclude that combining axial z-sweep image acquisition with deep learning-based image restoration enables high-throughput and high-quality fluorescence imaging of complex 3D biological samples.

Attention V-Net: A Modified V-Net Architecture for Left Atrial Segmentation

We propose a fully convolutional neural network based on the attention mechanism for 3D medical image segmentation tasks. It can adaptively learn to highlight the salient features of images that are useful for image segmentation tasks. Some prior methods enhance accuracy using multi-scale feature fusion or dilated convolution, which is basically artificial and lacks the flexibility of the model itself. Therefore, some works proposed the 2D attention gate module, but these works process 2D medical slice images, ignoring the correlation between 3D image sequences. In contrast, the 3D attention gate can comprehensively use the information of three dimensions of medical images. In this paper, we propose the Attention V-Net architecture, which uses the 3D attention gate module, and applied it to the left atrium segmentation framework based on semi-supervised learning. The proposed method is evaluated on the dataset of the 2018 left atrial challenge. The experimental results show that the Attention V-Net obtains improved performance under evaluation indicators, such as Dice, Jaccard, ASD (Average surface distance), and 95HD (Hausdorff distance). The result indicates that the model in this paper can effectively improve the accuracy of left atrial segmentation, therefore laying the foundation for subsequent work such as in atrial reconstruction. Meanwhile, our model is of great significance for assisting doctors in treating cardiovascular diseases.

In situ microstructural evolution of spruce wood during soda pulping using synchrotron X-ray tomography

Abstract A new laboratory reactor to perform in situ studies of structural changes in wood during soda pulping using synchrotron X-ray tomography is presented. The reactor is of recirculation type to provide stable reaction conditions and mimic the industrial situation. Experiments have been performed using this reactor in situ at a synchrotron microtomography beamline to provide sequences of 3D images from which measurement of wood cell wall thickness have been possible for the first time. The results showed that the cell wall thickness increased significantly in the early stage of pulping (&lt;10 min), which is due to the transportation of cooking chemicals through the tracheids, resin channels and pits into the cell wall, which is swollen with the increased pH. Subsequently, the cell wall thickness reduces over the processing time up to 60 min with a high rate, which is inferred to be due to the dissolution and transport of lignin and hemicellulose from the secondary walls, allowing for better transportation of active chemicals deep through the cell wall layers. After 60 min processing, the cell wall thickness reduction rate reduced, as dissolution of lignin and hemicelluloses from the cell walls ceased, while the remaining dissolution occurs mainly at the middle lamella.

ASMCNN: An efficient brain extraction using active shape model and convolutional neural networks

Brain extraction (skull stripping) is a challenging problem in neuroimaging. It is due to the variability in conditions from data acquisition or abnormalities in images, making brain morphology and intensity characteristics changeable and complicated. In this paper, we propose an algorithm for skull stripping in Magnetic Resonance Imaging (MRI) scans, namely ASMCNN, by combining the Active Shape Model (ASM) and Convolutional Neural Network (CNN) for taking full of their advantages to achieve remarkable results. Instead of working with 3D structures, we process 2D image sequences in the sagittal plane. First, we divide images into different groups such that, in each group, shapes and structures of brain boundaries have similar appearances. Second, a modified version of ASM is used to detect brain boundaries by utilizing prior knowledge of each group. Finally, CNN and post-processing methods, including Conditional Random Field (CRF), Gaussian processes, and several special rules are applied to refine the segmentation contours. Experimental results show that our proposed method outperforms current state-of-the-art algorithms by a significant margin in all experiments.

Fluoroscopic 3D Image Generation from Patient-Specific PCA Motion Models Derived from 4D-CBCT Patient Datasets: A Feasibility Study.

A method for generating fluoroscopic (time-varying) volumetric images using patient-specific motion models derived from four-dimensional cone-beam CT (4D-CBCT) images was developed. 4D-CBCT images acquired immediately prior to treatment have the potential to accurately represent patient anatomy and respiration during treatment. Fluoroscopic 3D image estimation is performed in two steps: (1) deriving motion models and (2) optimization. To derive motion models, every phase in a 4D-CBCT set is registered to a reference phase chosen from the same set using deformable image registration (DIR). Principal components analysis (PCA) is used to reduce the dimensionality of the displacement vector fields (DVFs) resulting from DIR into a few vectors representing organ motion found in the DVFs. The PCA motion models are optimized iteratively by comparing a cone-beam CT (CBCT) projection to a simulated projection computed from both the motion model and a reference 4D-CBCT phase, resulting in a sequence of fluoroscopic 3D images. Patient datasets were used to evaluate the method by estimating the tumor location in the generated images compared to manually defined ground truth positions. Experimental results showed that the average tumor mean absolute error (MAE) along the superior–inferior (SI) direction and the 95th percentile in two patient datasets were 2.29 and 5.79 mm for patient 1, and 1.89 and 4.82 mm for patient 2. This study demonstrated the feasibility of deriving 4D-CBCT-based PCA motion models that have the potential to account for the 3D non-rigid patient motion and localize tumors and other patient anatomical structures on the day of treatment.

Enhancement of 3D Point Cloud Contents Using 2D Image Super Resolution Network

Media technology has been developed to give users a sense of immersion. Recent media using 3D spatial data, such as augmented reality and virtual reality, has attracted attention. A point cloud is a data format that consists of a number of points, and thus can express 3D media using coordinates and color information for each point. Since a point cloud has a larger capacity than 2D images, a technology to compress the point cloud is required, i.e., standardized in the international standard organization MPEG as a video-based point cloud compression (V-PCC). V-PCC decomposes 3D point cloud data into 2D patches along orthogonal directions, and those patches are placed into a 2D image sequence, and then compressed using existing 2D video codecs. However, data loss may occur while converting a 3D point cloud into a 2D image sequence and encoding this sequence using a legacy video codec. This data loss can cause deterioration in the quality of a reconstructed point cloud. This paper proposed a method of enhancing a reconstructed point cloud by applying a super resolution network to the 2D patch image sequence of a 3D point cloud.

Towards a Fair Evaluation of Feature Extraction Algorithms Robustness in Structure from Motion

Structure from Motion is a pipeline for 3D reconstruction in which the true geometry of an object or a scene is inferred from a sequence of 2D images. As feature extraction is usually the first phase in the pipeline, the reconstruction quality depends on the accuracy of the feature extraction algorithm. Fairly evaluating the robustness of feature extraction algorithms in the absence of reconstruction ground truth is challenging due to the considerable number of parameters that affect the algorithms' sensitivity and the tradeoff between reconstruction size and error. The evaluation methodology proposed in this paper is based on two elements. The first is using constrained 3D reconstruction, in which only fixed numbers of extracted and matched features are passed to subsequent phases. The second is comparing the 3D reconstructions using size-error curves (introduced in this paper) rather than the value of reconstruction size, error, or both. The experimental results show that the proposed methodology is more transparent.