Texture Space Research Articles

A Planar Feature-Preserving Texture Defragmentation Method for 3D Urban Building Models

Oblique photogrammetry-based 3D modeling is widely used for large-scale urban reconstruction. However, textures generated with photogrammetric techniques often exhibit scattered and irregular characteristics, which lead to significant challenges with texture seams and UV map discontinuities, increasing storage requirements and affecting rendering quality. In this paper, we propose a planar feature-preserving texture defragmentation method designed specifically for urban building models. Our approach leverages the multi-planar topology of buildings to optimize texture merging and reduce fragmentation. The proposed approach is composed of three main stages: the extraction of planar features from texture fragments; the employment of these planar elements as guiding constraints for merging adjacent texture fragments within a two-dimensional texture space; and an enhanced texture-packing algorithm designed for more regular texture charts to systematically generate refined texture atlas. Experiments on various urban building models demonstrate that our method significantly improves texture continuity and storage efficiency compared to traditional approaches, with both quantitative and qualitative validation.

TriHuman: A Real-time and Controllable Tri-plane Representation for Detailed Human Geometry and Appearance Synthesis

Creating controllable, photorealistic, and geometrically detailed digital doubles of real humans solely from video data is a key challenge in Computer Graphics and Vision, especially when real-time performance is required. Recent methods attach a neural radiance field (NeRF) to an articulated structure, e.g., a body model or a skeleton, to map points into a pose canonical space while conditioning the NeRF on the skeletal pose. These approaches typically parameterize the neural field with a multi-layer perceptron (MLP) leading to a slow runtime. To address this drawback, we propose TriHuman a novel human-tailored, deformable, and efficient tri-plane representation, which achieves real-time performance, state-of-the-art pose-controllable geometry synthesis as well as photorealistic rendering quality. At the core, we non-rigidly warp global ray samples into our undeformed tri-plane texture space, which effectively addresses the problem of global points being mapped to the same tri-plane locations. We then show how such a tri-plane feature representation can be conditioned on the skeletal motion to account for dynamic appearance and geometry changes. Our results demonstrate a clear step toward higher quality in terms of geometry and appearance modeling of humans as well as runtime performance.

Reference-Based OCT Angiogram Super-Resolution With Learnable Texture Generation.

Optical coherence tomography angiography (OCTA) can visualize retinal microvasculature and is important to qualitatively and quantitatively identify potential biomarkers for different retinal diseases. However, the resolution of optical coherence tomography (OCT) angiograms inevitably decreases when increasing the field-of-view (FOV) given a fixed acquisition time. To address this issue, we propose a novel reference-based super-resolution (RefSR) framework to preserve the resolution of the OCT angiograms while increasing the scanning area. Specifically, textures from the normal RefSR pipeline are used to train a learnable texture generator (LTG), which is designed to generate textures according to the input. The key difference between the proposed method and traditional RefSR models is that the textures used during inference are generated by the LTG instead of being searched from a single reference (Ref) image. Since the LTG is optimized throughout the whole training process, the available texture space is significantly enlarged and no longer limited to a single Ref image, but extends to all textures contained in the training samples. Moreover, our proposed LTGNet does not require an Ref image at the inference phase, thereby becoming invulnerable to the selection of the Ref image. Both experimental and visual results show that LTGNet has competitive performance and robustness over state-of-the-art methods, indicating good reliability and promise in real-life deployment. The source code is available at https://github.com/RYY0722/LTGNet.

A Study on the Cavitation Effect of Elastic Material with Textured Surfaces under Fluid Lubrication Conditions

This study investigates the effect of the elastic surface micro-texture on the cavitation and lubrication characteristics of the friction pairs through theoretical and experimental research. Through numerical simulations and experiments, the influences of the elastic modulus and sliding speed on the lubrication performance of the friction pair are studied. The results show that under certain speed and load conditions, the friction coefficient of the elastic texture is smaller, and the lubrication performance is better than that of the rigid texture. Increasing the sliding speed and texture spacing properly can improve the lubrication performance of elastic friction pairs. In addition, as the elastic modulus decreases, the elastic deformation and oil film thickness increase, and the cavitation phenomenon becomes more significant. Thus, the lubrication performance of the friction pair is improved.

Effects of aggregate shape on the macrotexture and performance of chip seal: a laboratory study

Chip seal is an efficient maintenance strategy for bituminous pavements, with aggregate shape significantly impacting its embedment and performance, but there is limited quantification of its effects. Using the Aggregate Image Measurement System II (AIMS-II) for shape classification, this study investigated the influence of aggregate shape on chip seal's macrotexture and performance through a series of tests, including 3D laser scanning test, aggregate coverage test, skid resistance test, and sweep test, employing response surface methodology (RSM) for quantification. Results indicated that an abundance of flat aggregates deteriorates surface quality by increasing roughness and altering texture spacing, recommending their proportion be kept under 10%. Conversely, elongated aggregates enhance performance by enriching texture depth and sharpening surface peaks. Spearman rank correlation analysis identified the arithmetic mean peak curvature (Spc ) and the root mean square height (Sq ) as reliable measures for evaluating skid resistance and aggregate retention of chip seals, respectively.

Local highlight and shadow adaptively repairing GAN for illumination-robust makeup transfer

Recently, makeup transfer task has been widely explored with the development of deep learning. However, existing methods have shortcomings in more complex lighting situations in the real world because they do not consider the interference of lighting factors on facial features. To solve the above problem, we propose a local highlight and shadow adaptively repairing GAN for illumination-robust makeup transfer. We first map the 2D face images to UV representations and perform makeup transfer in the UV texture space, which explicitly removes the spatial misalignment to achieve pose and expression invariant makeup transfer. Furthermore, we take advantage of the face symmetry in the UV texture space to design an illumination repair module. It can adaptively repair the features affected by asymmetric local highlight and shadow based on a process of flipping and multi-layer attention fusion. In addition, the multi-layer attention maps are obtained by a pre-trained illumination classification network and hence have the ability to indicate local highlight and shadow areas. Comprehensive experiment results demonstrate the consistent effectiveness and clear advantages of our method, which significantly improve the robustness against local light effects and generate natural transfer results.

Least-Squares Estimation of Tangent Space for a Triangular Mesh

This paper presents a novel method for computing an orthonormal tangent space at every vertex of a triangular mesh provided with texture coordinates, which is essential in normal mapping. Our method employs least-squares estimation of rotation between two sets of corresponding points: one set from the positions of the 1-ring neighbors of a vertex in texture space and the other set from their corresponding positions in world space. This optimal rotation represents a local space transformation that defines the tangent space at the vertex. Consequently, our method ensures that the resulting tangent space is inherently orthonormal, eliminating the need for intricate operations such as averaging and orthonormalization, which are required in the previous methods. In addition, we introduce texture space alignment of triangles to address vertices on seams, which are inevitable in texture mapping to a closed surface mesh. Experimental results demonstrate the effectiveness of the proposed methods in various experiments.

Preparation of mechanically durable superhydrophobic aluminum surfaces by LST/MAO and chemical modification

In this paper, a superhydrophobic surface with mechanical durability was prepared on 6061 aluminum (Al) alloy by combining laser surface texturing (LST) and micro-arc oxidation (MAO) techniques followed by chemical immersion treatment. The effects of processing on Al alloys with different texturing spacings on the surface morphology, roughness, surface wettability, and corrosion resistance of the subsequently formed composite coatings were analyzed. The results show that a superhydrophobic surface was obtained with the water contract angle (WCA) of 158.3 ° and the roll-off angle of 9.5 ° at a texture spacing of 300 μm. This was due to the fact that the surface microroughness texturization process created by LST on the surface increased the generation of surface nanostructures, and combined with the natural nanostructure possessed by MAO, unique " double " nanostructure was formed on the surface. This surface structure increased the area of fluoride attachment, reduced the solid-liquid contact area, and decreased the adhesion of droplets to the surface, resulting in higher hydrophobicity. Electrochemical corrosion experiment showed that the corrosion current density of LM-300 was 2 orders of magnitude lower than that of the LM-0 sample, clearly demonstrating better corrosion resistance. In addition, the prepared superhydrophobic surface presented excellent mechanical durability, and in the ceramic zirconia cyclic abrasion experiment, the superhydrophobic surface was able to withstand 61 cycles of abrasion at a pressure of about 2.5 kPa.

Evaporation and wetting behavior of water on the laser-textured silicon substrate

It is important to elucidate the impact of surface micromorphology on the evaporation mechanism and behavior to design rational micromorphologies for enhancing/regulating evaporation. In this study, we investigated the wetting and evaporation behaviors of water droplets on monocrystalline silicon surfaces with concentric circular textures etched using a laser engraving system at varying spacing intervals. Only when the texture spacing overlapped did it exhibit a significantly increased apparent surface energy and evaporation rate. The droplet volume decreased consistently at a constant evaporation rate at different temperatures, and the process involved two stages: constant contact radius (CCR) and constant contact angle (CCA). Laser etching increases the thickness of the oxide film from 10 to 377 nm, resulting in enhanced hydrophilicity. For millimeter-sized droplets, microscopic capillary phenomena in the vicinity of the triple line dominated the evaporation behavior rather than liquid/gas interface evaporation.

Comparative Study on the tribological performance and wear behaviour of hypereutectic Al–Si cylinder liner surfaces textured using micro-drilling and mechanical indentation-based approaches

Thermally-induced microstructural changes and the requirement of expensive equipment are the deterring aspects of using laser-based texturing for tribological applications. This study presents two texturing methods based on mechanical indentation and micro drilling on hypereutectic Al–Si cylinder liner surfaces. Etched hypereutectic Al–Si specimens were textured at three distinct texture spacings (1 mm, 1.5 mm, and 2 mm) and tested against a piston ring using a linear reciprocating tribometer at 30 °C, 80 °C, and 160 °C under boundary lubrication regime to study their tribological behaviour. Forty-eight experimental runs were performed based on the design of experiments method to investigate the effect of the texture generation method, texture spacing, and temperature on the friction and wear behaviour of the textured cylinder liner against a chrome-coated piston ring, and the results are compared with bare, unetched and untextured Al–Si specimens. Wear rates and wear mechanisms of Al–Si cylinder liners subjected to both texturing approaches under sliding conditions were investigated. Mechanical indentation with texture spacing of 1 mm exhibited optimum tribological performance with low friction coefficient and wear values in comparison to micro-drilled and non-textured liner surfaces. Texture spacing of 2 mm is observed to show a negative effect on tribological performance for every experimental run.

Connectedness in graded ditopological texture spaces

The aim of this paper is to introduce two different types of connectedness notions for graded ditopological texture spaces: the connectedness function which gives the grade of connectedness of a set and the connectedness spectrum by means of spectrum idea. Also, the properties of these connectedness notions and their relationships with the connectedness notion in ditopological case are investigated. Further, the relation between these two different types of connectedness notions is studied.

MuNeRF: Robust Makeup Transfer in Neural Radiance Fields.

There has been a high demand for facial makeup transfer tools in fashion e-commerce and virtual avatar generation. Most of the existing makeup transfer methods are based on the generative adversarial networks. Despite their success in makeup transfer for a single image, they struggle to maintain the consistency of makeup under different poses and expressions of the same person. In this paper, we propose a robust makeup transfer method which consistently transfers the makeup style of a reference image to facial images in any poses and expressions. Our method introduces the implicit 3D representation, neural radiance fields (NeRFs), to ensure the geometric and appearance consistency. It has two separate stages, including one basic NeRF module to reconstruct the geometry from the input facial image sequence, and a makeup module to learn how to transfer the reference makeup style consistently. We propose a novel hybrid makeup loss which is specially designed based on the makeup characteristics to supervise the training of the makeup module. The proposed loss significantly improves the visual quality and faithfulness of the makeup transfer effects. To better align the distribution between the transferred makeup and the reference makeup, a patch-based discriminator that works in the pose-independent UV texture space is proposed to provide more accurate control of the synthesized makeup. Extensive experiments and a user study demonstrate the superiority of our network for a variety of different makeup styles.

STAR-TM: STructure Aware Reconstruction of Textured Mesh From Single Image.

We present a novel method for single-view 3D reconstruction of textured meshes, with a focus to address the primary challenge surrounding texture inference and transfer. Our key observation is that learning textured reconstruction in a structure-aware and globally consistent manner is effective in handling the severe ill-posedness of the texturing problem and significant variations in object pose and texture details. Specifically, we perform structured mesh reconstruction, via a retrieval-and-assembly approach, to produce a set of genus-zero parts parameterized by deformable boxes and endowed with semantic information. For texturing, we first transfer visible colors from the input image onto the unified UV texture space of the deformable boxes. Then we combine a learned transformer model for per-part texture completion with a global consistency loss to optimize inter-part texture consistency. Our texture completion model operates in a VQ-VAE embedding space and is trained end-to-end, with the transformer training enhanced with retrieved texture instances to improve texture completion performance amid significant occlusion. Extensive experiments demonstrate higher-quality textured mesh reconstruction obtained by our method over state-of-the-art alternatives, both quantitatively and qualitatively, as reflected by a better recovery of texture coherence and details.

Effect of surface texture spacing on interface heat transfer and tensile property of laser‐welded steel/CFRTP joint

AbstractMetal‐polymer hybrid joints can contribute to weight reduction and have potential use in transportation industries. In this work, laser texturing was used to enhance bonding strength of laser‐welded 304 stainless steel/carbon fiber reinforced thermoplastics (CFRTP) joint. The tight relationship between surface texture spacing and porosity characteristic as well as tensile property of joint was systematically investigated. The temperature field distribution during welding process was simulated and the mechanism of porosity suppression depending on grid spacing was discussed. The result showed that the number of pores at cross‐section decreased first and then rose with the increase of micro‐structure spacing, which corresponded to the variation trend of bonding strength and was inconsistent with the evolution of connecting area. The joint achieved the minimum porosity defect and reached maximum fracture load of 2594 N when the grid spacing was 1.2 mm, while the maximum joint width of 9.28 mm was obtained when 0.4 mm spacing was adopted, indicating that the joint quality rather than mechanical interlocking governed the mechanical property of joint. Appropriate interface contact conductance (TCC) related to texture spacing could optimize the interface heat dissipation rate, and was the key factor to efficiently control the shrinkage porosity. The TCC of small or large grid spacing was too high or too small, resulting in failure of the heat transfer path through the interface to metal during cooling process. Moreover, the proper texture spacing improved the uniformity of joint strain distribution in tensile‐shear testing, which benefited joint strength.Highlights Laser‐textured grid pattern spacing affected number and distribution of pores. Heat dissipation rate varied with various spacing at joint interface. 1.2 mm spacing texture reduced stress concentration during tensile process.

IMPROVING THE LONG-TERM DURABILITY OF POLYMERS USED IN BIOMEDICAL APPLICATIONS.

Hydrophobic surfaces can improve the long-term mechanical response of polymers by delaying their degradation caused by moisture absorption over time. This improvement in long-term mechanical performance can significantly increase the lifespan of polymers used in various biomedical applications, such as total joint replacement prostheses applications. Although a number of surface modification techniques have been developed over the years, such as introduction of various textures on the surface; their specific influences on hydrophobicity enhancement as well as long-term mechanical performance are yet to be fully understood. In this study, surface textures, with variation in type and geometry, are introduced on model Ultrahigh Molecular Weight Polyethylene (UHMWPE) and High Density Polyethylene (HDPE) surfaces to study the effect of surface modification on hydrophobicity and long-term mechanical performance under environmental conditions. The results show that introduction of surface textures significantly improves the hydrophobicity of model polymers. Texture length or diameter significantly affects the improvement in hydrophobicity. However, texture spacing does not have significant influence on the improvement in hydrophobicity. How this improvement in hydrophobicity facilitates improving the long-term mechanical performance under environmental conditions is investigated. The study provides useful guidelines to improve the long-term mechanical response of polymers for various applications, including biomedical applications.

Real‐Time Rendering of Glinty Appearances using Distributed Binomial Laws on Anisotropic Grids

AbstractIn this work, we render in real‐time glittery materials caused by discrete flakes on the surface. To achieve this, one has to count the number of flakes reflecting the light towards the camera within every texel covered by a given pixel footprint. To do so, we derive a counting method for arbitrary footprints that, unlike previous work, outputs the correct statistics. We combine this counting method with an anisotropic parameterization of the texture space that reduces the number of texels falling under a pixel footprint. This allows our method to run with both stable performance and 1.5× to 5× faster than the state‐of‐the‐art.

Conical Grinding Wheel Ultrasonic-Assisted Grinding Micro-Texture Surface Formation Mechanism

The rotating ultrasonic-assisted grinding (RUAG) experiment of the conical grinding wheel generated the intermittent pit-shaped micro-texture on the surface of the workpiece, reducing thermal damage and improving the lubrication characteristics compared with conventional grinding (CG). To further optimize the surface properties, this paper studied the formation mechanism of micro-texture. This study used as basis the theory that micro-debris volume equals the macroscopic material removal one to establish the mathematical equation of grinding depth. Thereafter, formulas of micro-texture feature parameters, including pit length, pit depth, and texture spacing were deduced. The solved microscopic grinding depth was alternatingly positive and negative, indicating that the alternating separation between the grinding grain and workpiece caused intermittent pits in the grinding. Through response surface analysis (RSA), this paper analyzed the relationships among macroscopic grinding depth, micro-texture feature parameters, and machining parameters (i.e., amplitude, feed rate, and rotational speed). Single-factor experiments of machining parameters, with finite element simulation and experiment methods, were performed to verify the theoretical micro-texture features. The simulated program formed three-dimensional surfaces with micro-textures. Their measurement results were consistent with the theoretical ones. Experimental results proved that the range of pit length covers the theoretical ones, further verifying the accuracy of the grinding depth model. For this grinding wheel, the 8–10 μm amplitude was optimal for better roughness, lubrication, and thermal damage. Roughness was improved when increasing the rotational speed or reducing the feed rate based on the experiment. If the rotational speed and feed rate exceed the limiting values, then continuous grinding will break down the abrasive grains and even damage the cubic boron nitride (CBN) coating. Experimental results likewise showed that the pit shape was closely related to the surface properties, which deserves further investigation.

Comparative study on single-objective optimization and multi-objective optimization of convex textured friction couple performance

To improve the friction property of the friction pair of the hydrostatic thrust bearing, the surface with convex textures is designed at the bottom of the oil cavity, and the effect of convex textures on the interstitial oil film performance is analyzed. The interstitial oil film in contact with convex textures is simulated and studied by the computational fluid dynamics method. The study shows that the oil cavity with the convex structures can significantly improve the friction characteristics of the gap oil film in the hydrostatic thrust bearing. In order to further study the effect of texture parameters (texture radius, texture spacing , texture quantity and texture area ratio ) on its performance, the method based on the full factor test is used for single objective optimization, and the methods based on the BBD response surface and the NSGA-II algorithm are used for multiple target collaborative optimization. The full factor test with the main effect shows that the best combination with the bearing capacity is 0.5 mm, 7 mm, 7 and 1.6%, and the best combination with the rigidity is 0.3 mm, 5 mm, 5 and 1.13%. The influence of textures on the maximum temperature of oil film is basically unchanged and the bearing capacity is in inverse proportion to the friction factor. When considering the interaction between texture parameters, the BBD response surface method is used for multi-objective optimization. The study shows that the texture radius is 0.7 mm, the texture spacing is 7 mm, the quantity of textures is 6.2, and the area ratio is 3.14%, the optimal response values can be obtained, which the bearing capacity is 8519.31 N and the rigidity is 1.31868 E + 12 N m−1. The multi-objective optimization analysis of the NSGA-II algorithm based on the BBD response surface model shows that the algorithm can obtain a Pareto solution set. Each set of solutions obtained by the NSGA-II algorithm is the optimal solution. Both the BBD response surface method and the NSGA-II algorithm can be used to solve multi-objective problems.

Non-Rigid Point Cloud Matching Based on Invariant Structure for Face Deformation

In this paper, we present a non-rigid point cloud matching method based on an invariant structure for face deformation. Our work is guided by the realistic needs of 3D face reconstruction and re-topology, which critically need support for calculating the correspondence between deformable models. Our paper makes three main contributions: First, we propose an approach to normalize the global structure features of expressive faces using texture space properties, which decreases the variation magnitude of facial landmarks. Second, we make a modification to the traditional shape context descriptor to solve the problem of regional cross-mismatch. Third, we collect a dataset with various expressions. Ablation studies and comparative experiments were conducted to investigate the performance of the above work. In face deformable cases, our method achieved 99.89% accuracy on our homemade face dataset, showing superior performance over some other popular algorithms. In this way, it can help modelers to build digital humans more easily based on the estimated correspondence of facial landmarks, saving a lot of manpower and time.

On-Tube Attribute Visualization for Multivariate Trajectory Data.

Stylized tubes are an established visualization primitive for line data as encountered in many scientific fields, ranging from characteristic lines in flow fields, fiber tracks reconstructed from diffusion tensor imaging, to trajectories of moving objects as they arise from cyber-physical systems in many engineering disciplines. Typical challenges include large data set sizes demanding for efficient rendering techniques as well as a large number of attributes that cannot be mapped simultaneously to the basic visual attributes provided by a tube-based visualization. In this work, we tackle both challenges with a new on-tube visualization approach. We improve recent work on high-quality GPU ray casting of Hermite spline tubes supporting ambient occlusion and extend it by a new layered procedural texturing technique. In the proposed framework, a large number of data set attributes can be mapped simultaneously to a variety of glyphs and plots that are embedded in texture space and organized in layers. Efficient rendering with minimal data transfer is achieved by generating the glyphs procedurally and drawing them in a deferred shading pass. We integrated these techniques in a prototype visualization tool that facilitates flexible mapping of data set attributes to visual tube and glyph attributes. We studied our approach on a variety of example data from different fields and found it to provide a highly adaptable and extensible toolbox to quickly craft tailor-made tube-based trajectory visualizations.