Perlin Noise Research Articles

Cutting-edge techniques in 3D modeling and animation: Leveraging mathematical models and advanced software tools

Abstract. This paper explores the advancements in computer animation technology, focusing on 3D modeling and animation. It delves into the core aspects of character design, environment modeling, and animation rigging, emphasizing the mathematical models and algorithms that enhance realism and efficiency. Key techniques discussed include Bezier curves and spline interpolation for anatomy and proportions, Perlin noise and fractal algorithms for texturing, and Inverse Kinematics (IK) and Forward Kinematics (FK) for rigging. Additionally, the paper examines procedural generation and fluid dynamics simulations for environment modeling and the integration of motion capture data. The use of software tools like Blender, Autodesk Maya, and Houdini is highlighted. This study aims to provide a comprehensive understanding of the current state of 3D animation technology and its future directions.

Improving semantic segmentation accuracy in thin cloud interference scenarios by mixing simulated cloud-covered samples

Thin cloud interference presents a significant challenge for the semantic segmentation of optical satellite imagery, which directly degrades the model accuracy and causes difficulties in sample selection. This paper generated a dataset named Populus euphratica and Tamarix chinensis discrimination (PTD), containing both cloudless and thin cloud scenarios. Based on this PTD dataset, an enhanced Atmospheric Scattering Model with Nonlinear Optimization (ASM_NL) was proposed to simulate high-fidelity thin clouds by incorporating two vital nonlinear terms: the point spread function and the Perlin noise. Additionally, we adopt a strategy of mixing simulated thin cloud-covered images (STCI) into the training set at a certain proportion to improve the semantic segmentation accuracy in thin cloud-covered scenarios. The conclusions are as follows: 1) ASM_NL can simulate high-fidelity clouds at an average Jensen-Shannon distance of 0.0699. 2) When dealing with medium- and high-cloud density datasets, mixing STCI proved to be more effective than cloud removal in mitigating thin cloud interference, resulting in average macro F1 score improvements of 0.164 and 0.094, respectively. 3) The semantic segmentation accuracy improved significantly by mixing STCI with a minimal proportion of 1/60, demonstrating the activation of model transfer capabilities. This study provides a concise and efficient methodology for effectively mitigating thin cloud interference in deep learning-based optical satellite imagery analysis.

Natural generative noise diffusion model imputation

Imputation is a critical method for enhancing dataset quality, essential for ensuring accurate analysis and insights. This research proposes an advanced imputation algorithm utilizing a Diffusion Model enhanced with Perlin noise generation. We introduce Perlin noise at each step of the diffusion process and incorporate a cosine scheduler to optimize performance. Our approach demonstrates improvements in imputing non-normal data, validated through tests on ten real datasets. Due to the substantial slope of distribution properties produced by perlin noise, noisy data gradually contaminates nonnormally distributed data, making it more like to a Gaussian distribution. The Perlin noise distribution increases the normality of the noisy data provided noise when it enters the deep neural process of diffusion imputation. We assess our proposed approach by simulating the missing data rate using three scenarios: Missing Completely at Random (MCAR), Missing Not At Random (MNAR), and Missing at Random (MAR). Every case is handled similarly, with 20 % to 80 % missing data. Compared to other deep learning imputation methods, our proposed methods and improvements contribute to lowering the RMSE value up to 10 % on non-normal distributed data imputation.

A Lightweight CNN Based on Axial Depthwise Convolution and Hybrid Attention for Remote Sensing Image Dehazing

Hazy weather reduces contrast, narrows the dynamic range, and blurs the details of the remote sensing image. Additionally, color fidelity deteriorates, causing color shifts and image distortion, thereby impairing the utility of remote sensing data. In this paper, we propose a lightweight remote sensing-image-dehazing network, named LRSDN. The network comprises two tailored, lightweight modules arranged in cascade. The first module, the axial depthwise convolution and residual learning block (ADRB), is for feature extraction, efficiently expanding the convolutional receptive field with little computational overhead. The second is a feature-calibration module based on the hybrid attention block (HAB), which integrates a simplified, yet effective channel attention module and a pixel attention module embedded with an observational prior. This joint attention mechanism effectively enhances the representation of haze features. Furthermore, we introduce a novel method for remote sensing hazy image synthesis using Perlin noise, facilitating the creation of a large-scale, fine-grained remote sensing haze image dataset (RSHD). Finally, we conduct both quantitative and qualitative comparison experiments on multiple publicly available datasets. The results demonstrate that the LRSDN algorithm achieves superior dehazing performance with fewer than 0.1M parameters. We also validate the positive effects of the LRSDN in road extraction and land cover classification applications.

Unpaired Remote Sensing Image Dehazing Using Enhanced Skip Attention-Based Generative Adversarial Networks with Rotation Invariance

Remote sensing image dehazing aims to enhance the visibility of hazy images and improve the quality of remote sensing imagery, which is essential for various applications such as object detection and classification. However, the lack of paired data in remote sensing image dehazing enhances the applications of unpaired image-to-image translation methods. Nonetheless, the considerable parameter size of such methods often leads to prolonged training times and substantial resource consumption. In this work, we propose SPRGAN, a novel approach leveraging Enhanced Perlin Noise-Based Generative Adversarial Networks (GANs) with Rotation Invariance to address these challenges. Firstly, we introduce a Spatial-Spectrum Attention (SSA) mechanism with Skip-Attention (SKIPAT) to enhance the model’s ability to interpret and process spectral information in hazy images. Additionally, we have significantly reduced computational overhead to streamline processing. Secondly, our approach combines Perlin Noise Masks in pre-training to simulate real foggy conditions, thereby accelerating convergence and enhancing performance. Then, we introduce a Rotation Loss (RT Loss) to ensure the model’s ability to dehaze images from different angles uniformly, thus enhancing its robustness and adaptability to diverse scenarios. At last, experimental results demonstrate the effectiveness of SPRGAN in remote sensing image dehazing, achieving better performance compared to state-of-the-art methods.

Perlin noise generation of physiologically realistic cardiac fibrosis

Fibrosis, a pathological increase in extracellular matrix proteins, is a significant health issue that hinders the function of many organs in the body, in some cases fatally. In the heart, fibrosis impacts on electrical propagation in a complex and poorly predictable fashion, potentially serving as a substrate for dangerous arrhythmias. Individual risk depends on the spatial manifestation of fibrotic tissue, and learning the spatial arrangement on the fine scale in order to predict these impacts still relies upon invasive ex vivo procedures. As a result, the effects of spatial variability on the symptomatic impact of cardiac fibrosis remain poorly understood. In this work, we address the issue of availability of such imaging data via a computational methodology for generating new realisations of cardiac fibrosis microstructure. Using the Perlin noise technique from computer graphics, together with an automated calibration process that requires only a single training image, we demonstrate successful capture of collagen texturing in four types of fibrosis microstructure observed in histological sections. We then use this generator to quantitatively analyse the conductive properties of these different types of cardiac fibrosis, as well as produce three-dimensional realisations of histologically-observed patterning. Owing to the generator’s flexibility and automated calibration process, we also anticipate that it might be useful in producing additional realisations of other physiological structures.

Continuous Phase Denoising via Deep Learning Based on Perlin Noise Similarity in Digital Holographic Microscopy

Continuous Phase Denoising via Deep Learning Based on Perlin Noise Similarity in Digital Holographic Microscopy

Investigation of the Influence of Machining Parameters and Surface Roughness on the Wettability of the Al6082 Surfaces Produced with WEDM.

Electrical Discharge Machining (EDM) is a non-conventional machining technique, capable of processing any kind of conductive material. Recently, it has been successfully utilized for producing hydrophobic characteristics in inherently hydrophilic metallic materials. In this work, Wire Electrical Discharge Machining (WEDM) was utilized for producing hydrophobic characteristics on the surface of the aluminum alloy 6082, and various parameters that can affect wettability were investigated. Adopting an orthogonal Taguchi approach, the effects of the process parameter values of peak current, pulse-on time, and gap voltage on the contact angles of the machined surfaces were investigated. After machining, all samples were observed to have obtained hydrophobic properties, reaching contact angles up to 132°. The peak current was identified as the most influential parameter regarding the contact angle, while the gap voltage was the less influential parameter. A contact angle variation of 30° was observed throughout different combinations of machining parameters. Each combination of the machining parameters resulted in a distinct surface morphology. The samples with moderate roughness values (3.4 μm > Sa > 5.7 μm) were found to be more hydrophobic than the samples with high or low values, where the contact angle was measured under 115°. In addition, the finite element modeling of the experimental setup, with parametric surfaces of uniform random and Perlin noise types of roughness, was implemented. Time dependent simulations coupling phase field and laminar flow for the modelingof the wetting of surfaces with different surface roughness characteristics showed that an increase in the Sa roughness and total wetted area can lead to an increase in the contact angle. The combination of experimental and computational results suggests that the complexity of the wettability outcomes of aluminum alloy surfaces processed with WEDM lies in the interplay between variations of the surface chemical composition, roughness, micro/nano morphology, and the surface capability of forming a composite air/water interface.

Quantifying robustness: 3D tree point cloud skeletonization with smart-tree in noisy domains

Extracting tree skeletons from 3D tree point clouds is challenged by noise and incomplete data. While our prior work (Dobbs et al., in: Iberian conference on pattern recognition and image analysis, Springer, Berlin, pp. 351–362, 2023) introduced a deep learning approach for approximating tree branch medial axes, its robustness against various types of noise has not been thoroughly evaluated. This paper addresses this gap. Specifically, we simulate real-world noise challenges by introducing 3D Perlin noise (to represent subtractive noise) and Gaussian noise (to mimic additive noise). To facilitate this evaluation, we introduce a new synthetic tree point cloud dataset, available at https://github.com/uc-vision/synthetic-trees-II. Our results indicate that our deep learning-based skeletonization method is tolerant to both additive and subtractive noise.

An algorithm to generate 2D bathymetry of an Alpine river for habitat suitability assessment.

Here we present an original approach to generate 2D high detail riverbed based on a drone photogrammetric survey, and RTK bathymetry measurements for Mera river in the Italian Alps. The aim is to better represent macro-roughness and riverbed structure of the river, also extending it to an ungauged area. Specifically, we apply a step-by-step approach. I) Depth and average slope of the riverbed were calculated from bathymetry data. II) Thus, a trapezoidal channel with constant slope and variable width was defined using the drone images. III) Riffle-pool sequence was assessed as a function of river width and applied to the generated channel. IV) Finally, the semi-random Perlin Noise was added to recreate riverbed irregularities in the natural stream. HEC-RAS 2D hydraulic software was then implemented to assess spatialized water depth and velocity. The proposed methodology could be quite relevant in river hydraulics to decouple roughness coefficient from water submergence, and in Physical Habitat Simulation Model (PHABSIM), where the dependency of the output is not linear with hydraulic parameters (i.e. water depth and velocity). Indeed, we apply PHABSIM for a case study of a stretch of the river and results are compared with a previous environmental study for Mera river.

Research on the generation method of seawater sound velocity model based on Perlin noise

Research on the generation method of seawater sound velocity model based on Perlin noise

Mixed noise-guided mutual constraint framework for unsupervised anomaly detection in smart industries

Large-scale sensor and data acquisition systems, integrated with deep learning methodologies, play a pivotal role in enhancing the sustainability and security of smart city environments, exemplifying the critical significance of anomaly detection techniques. Anomaly detection in complex industrial scenarios presents various challenges, such as intricate working environments, limited anomaly samples, and lack of a priori information. Unsupervised anomaly detection based on knowledge distillation enables anomaly detection using only normal samples. However, the similarity in structure between teacher and student models, along with identical input data flow, hampers accurate anomaly detection and localization. To address these issues, we propose MNMC, an unsupervised anomaly detection model consisting of a mixed noise generation module emulating real defects, a mutual constraint module, and an anomaly segmentation module. Firstly, to enhance the student network’s ability to learn robust features, we construct a hybrid noise model comprising dead-leaves noise and perlin noise. This generates features with structural texture and distributional characteristics closer to real anomalies. Secondly, we design a mutual constraint framework to further improve the learning ability of the student network for normal features by constraining representations containing only a single noise. Lastly, for the detection of anomalies at different scales, we propose a new evaluation metric based on equal importance of normal and anomalous regions. Through ablation experiments, we demonstrate the effectiveness of the simulated real defect generation module and the mutual constraints module. Performance experiments on the MVTec dataset show that our method achieves competitive results compared to the current state-of-the-art anomaly detection methods.

Simulation of breast lesions based upon fractal Perlin noise

PurposeSteadily increasing use of computational/virtual phantoms in medical physics has motivated expanding development of new simulation methods and data representations for modelling human anatomy. This has emphasized the need for increased realism, user control, and availability. In breast cancer research, virtual phantoms have gained an important role in evaluating and optimizing imaging systems. For this paper, we have developed an algorithm to model breast abnormalities based on fractal Perlin noise. We demonstrate and characterize the extension of this approach to simulate breast lesions of various sizes, shapes, and complexity. Materials and methodRecently, we developed an algorithm for simulating the 3D arrangement of breast anatomy based on Perlin noise. In this paper, we have expanded the method to also model soft tissue breast lesions. We simulated lesions within the size range of clinically representative breast lesions (masses, 5–20 mm in size). Simulated lesions were blended into simulated breast tissue backgrounds and visualized as virtual digital mammography images. The lesions were evaluated by observers following the BI-RADS assessment criteria. ResultsObservers categorized the lesions as round, oval or irregular, with circumscribed, microlobulated, indistinct or obscured margins. The majority of the simulated lesions were considered by the observers to have a realism score of moderate to well. The simulation method provides almost real-time lesion generation (average time and standard deviation: 1.4 ± 1.0 s). ConclusionWe presented a novel algorithm for computer simulation of breast lesions using Perlin noise. The algorithm enables efficient simulation of lesions, with different sizes and appearances.

Simulation of Laser Profilometer Measurements in the Presence of Speckle Using Perlin Noise.

In the manufacturing industry, inspection systems play a crucial role in ensuring product quality. High-resolution profilometric sensors have become increasingly popular for inspection due to their ability to provide detailed surface information. However, the development and testing of inspection systems can be costly and time-consuming. This paper presents the development of a simulation of an inspection system using a high-resolution profilometric sensor. A geometrical and noise model is proposed to simulate the readings of any actual profilometric sensor. The model replicates the sensor's movement on the CAD model of the inspected part. The model incorporates the physical properties of the sensor and combines noise sources from sensor uncertainty and speckle noise induced by the roughness of the material. Our contribution lies in noise modeling. This work proposes a combination of Perlin noise to simulate the speckle noise and Gaussian noise for the uncertainty-related noise. Perlin noise is generated based on the surface roughness parameters of the inspected part. The accuracy of the simulation system is evaluated by comparing the simulated scans with real scans. The results highlight the ability to simulate real scans of different parts, using commercial sensor specifications and the CAD model of the inspected part.

Neutron multiplication and reactor kinetics parameters in stochastic media based on randomized noise functions

The modelling of stochastic media is of considerable interest for criticality safety and reactor physics applications. Novel methods for modelling highly disordered, random heterogeneous mixtures based on randomized Weierstrass functions and Perlin noise have been implemented in the MONK® Monte Carlo code using Woodcock tracking. Perlin noise in particular is shown to be well suited to the application, efficiently producing random geometries with much greater physical realism than the artificial nature of alternative methods. The effect of geometry randomization on neutron multiplication and reactor kinetics parameters in a simple benchmark configuration has been investigated, and results are compared with previous research based on tessellation algorithms. While the results are found to be broadly consistent with previous work, the new methods presented here offer significant benefits in terms of increased physical realism, conservation of material volume fractions, computational efficiency and ease of use.

PROCEDURAL GENERATION IN 2D METROIDVANIA GAME WITH ANSWER SET PROGRAMMING AND PERLIN NOISE

Designing metroidvania games often poses a unique challenge to video game developers, namely the difficulty of consistently preventing soft-locking, which hinders or blocks the player’s ability to traverse through levels effectively [1]. As a result, many turn to hand-making all levels to ensure the level’s traversability, but in the process often forsaking the ability to rely on procedural generation to lessen the time and burden on human game developers [2]. On the other hand, when developers rely on popular ways of procedural generation such as using perlin noise, they find themselves unable to control those procedural algorithms to guarantee certain characteristics of the outputs such as traversability [3]. Our paper aims to present a procedural solution that can also effectively guarantee the traversability of the generated level. Our method uses Answer Set Programming (ASP) to verify generation based on restrictions we place, guaranteeing the outcome to be what we want [4]. The generation of a level is divided into rooms, which are first mapped out in a graph to ensure traversability from a starting room to an ending boss area. The rooms’ geometry is then generated accordingly to create the full level. Using perlin noise, we were also able to create a demonstration of how traversability works in another form of procedural generation, and compare it with our methodology to identify strengths and weaknesses. To demonstrate our method, we applied our solution as well as the perlin noise algorithm to a 2D metroidvania game made in the Unity game engine and conducted quantitative tests on the ASP method to assess how well our method works as a level generator [5].

Implementasi Generate Map dan Pemunculan Objek secara Acak pada Game 3D menggunakan Bahasa C# dan Metode Perlin Noise di Unity: Studi Kasus pada Game Development

<p><span style="text-decoration: underline;"><em>Perlin noise algorithm is used to generate noise on the map surface, creating natural effects in 3D games. In this research, a C# script code has been implemented in Unity that can generate maps and spawn random objects in the game. The research results demonstrate that the implementation of map generation and random object spawning techniques can enhance gameplay quality and provide a more immersive playing experience for users. This research aims to contribute to game development on the Unity platform as well as the development of map This research explores the implementation of procedural content generation (PCG) techniques using C# programming language and Perlin noise method in Unity to generate map and random object spawning in 3D games. The main objective of this research is to develop PCG techniques that can be applied to game development. The generation and random object spawning techniques in 3D games using Perlin noise method.</em></span></p>

Procedural Terrain Generation by Sampling a 2D Monochrom Perlin Noise Map in Unity

This article presents a study on procedural terrain generation using Perlin noise in the Unity game engine, building upon prior research and established techniques [1,2]. The objective of the this study is to create realistic and visually appealing landscapes by leveraging algorithmic generation [3]. By utilizing a two dimensional monochrome Perlin noise map, the algorithm generates terrains with organic features such as hills, valleys, and mountains [4]. The research employs the Unity game engine, which offers a wide range of tools and technologies for implementing procedural generation algorithms [5].
 The performance analysis conducted during this study yielded important insights. The execution time test revealed that the algorithm's execution time increased significantly with larger grid sizes, emphasizing the need to consider the scale and resolution of the terrains [6]. This finding highlights the trade-off between generating detailed terrains and the time required for the algorithm to complete its computations. Additionally, the memory usage test demonstrated a quadratic relationship between memory usage and grid size, indicating the necessity of efficient memory management [7] for generating higher-resolution terrains. Optimizing memory usage is crucial to avoid excessive consumption and ensure efficient resource utilization.
 These findings from the performance analysis provide valuable guidance for optimizing and refining the algorithm discussed in this article. Techniques such as algorithmic refinements, parallelization [8,6], and memory optimization strategies can be employed to reduce execution times and minimize memory overhead.
 By understanding the algorithm's performance characteristics and leveraging the insights gained from the analysis, developers can make informed decisions to generate visually compelling and diverse landscapes within the Unity game engine.

A system for the validation of collision avoidance algorithm performance of autonomous ships

Adequate validations on intelligent ships are essential to guarantee navigation safety and efficiency. In this paper an emulated validation system is constructed to test collision avoidance ability of autonomous ships in open waters, coastal regions and archipelago areas with different traffic densities. A synthetic map generator is designed, the map meshing conbines the techniques from Voronoi Tessellation, Poisson-disk Sampling and Perlin Noise to build up more natural coastlines and detailed elevation data. To imitate random encounter scenarios, a new method is designed to maintain target ship quantity, to conduct various tests, 3 types of water geography, different ship behaviors as well as manual and automatic control modes are applied, during testing, each ship is designed to follow the planned routes which are generated arbitrarily and then smoothed. A validation scheme is put forward for comprehensive testing procedures. Finally, A set of experiments on the collision avoidance algorithm show the merits and drawbacks, this verifies the effectiveness of the validation system.

Procedural Content Generation pada Game Tower Defense menggunakan Perlin Noise dan Algoritma Floyd Warshall

To distinguish each level, tower defense games require map design, enemy travel routes, and enemy wave designs. Manually designed designs require a lot of effort and time. To overcome this problem, procedural content generation is used to create maps automatically. Not all content can be created automatically, the content designed in this research includes portal design, tower design, enemy design, and tile design. The Map is created automatically using Perlin Noise to determine the type of tiles on the map. To produce a playable map in accordance with the minimum distance requirement of 45 tiles, the position of the player portal and enemy portal need to be checked using the Floyd-Warshall algorithm. The test results show that after 100 attempts, 25 trials need to be repeated because the distance between the portals does not meet the requirements. The average map creation time is 0.99 seconds. The enemy waves on each map also vary from the number of each type and the order in which the enemies come out.