Recent work in 3D deep learning has demonstrated that unsigned distance functions (UDFs) are a useful representation for 3D reconstruction and shape generation because they can represent surfaces with arbitrary topology. However, extracting meshes that preserve the intended topology, especially in the presence of non-manifold structures, remains challenging. We present DCx , an extension of the standard Dual Contouring (DC) method which was originally proposed for isosurface extraction from signed distance functions (SDFs). Standard DC operates on individual voxels and inserts one vertex per active cube, where activation is determined by detecting sign changes. To address the lack of sign information in UDFs, DCx adopts an optimization-based strategy for determining active cubes. It operates on each 2 × 2 × 2 voxel block, referred to as an expanded cube, and introduces a voxel-to-mesh lookup table that stores connectivity patterns based on local voxel configurations. This enables efficient triangle extraction using predefined templates. These changes improve upon DC by avoiding failure cases caused by unreliable active-cube detection in UDFs and by correcting mesh connections in non-manifold regions. As a result, DCx supports the extraction of both manifold and non-manifold surfaces from neural UDFs. DCx is conceptually simple and easy to implement. Experimental results show that DCx produces meshes with higher accuracy in a more robust way than existing methods, particularly on shapes with complex geometry or non-manifold structures. The source code is available at http://github.com/jjjkkyz/DCx.

Multi-layer perceptrons (MLPs) are a standard tool for learning and function approximation, but they inherently produce globally smooth outputs. Consequently, they struggle to represent functions that are continuous yet intentionally non-differentiable (i.e., functions with prescribed C 0 sharp features) without ad hoc post-processing. We present SharpNet , a modified MLP architecture that encodes user-specified sharp features by augmenting the network with an auxiliary feature function defined as the solution to Poisson's equation with jump Neumann boundary conditions. This feature function is evaluated via an efficient local integral and is fully differentiable with respect to the feature locations, allowing us to jointly optimize both the feature locations and the MLP parameters to recover the target function or geometry. This construction provides precise control over where non-differentiability occurs, enforcing the desired C 0 behavior at feature locations while preserving smoothness elsewhere. We validate SharpNet on 2D problems and 3D CAD reconstruction, and compare it with several state-of-the-art baselines. In both settings, SharpNet accurately recovers sharp edges and corners while remaining smooth away from them, whereas existing methods tend to blur gradient discontinuities. Qualitative and quantitative results demonstrate the effectiveness of our approach. Our project page, code and models are publicly available at https://sharpnettech.github.io.

While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and DCUDF for extracting the local minimal average distance surface. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces.

Unsigned distance fields (UDFs) are widely used in 3D deep learning due to their ability to represent shapes with arbitrary topology. While prior work has largely focused on learning UDFs from point clouds or multi-view images, extracting meshes from UDFs remains challenging, as the learned fields rarely attain exact zero distances. A common workaround is to reconstruct signed distance fields (SDFs) locally from UDFs to enable surface extraction via Marching Cubes. However, this often introduces topological artifacts such as holes or spurious components. Moreover, local SDFs are inherently incapable of representing non-manifold geometry, leading to complete failure in such cases. To address this gap, we propose MIND ($\mathrm{\underline{M}aterial}$ $\mathrm{\underline{I}nterface}$ $\mathrm{from}$ $\mathrm{\underline{N}on}$-$\mathrm{manifold}$ $\mathrm{\underline{D}istance}$ $\mathrm{fields}$), a novel algorithm for generating material interfaces directly from UDFs, enabling non-manifold mesh extraction from a global perspective. The core of our method lies in deriving a meaningful spatial partitioning from the UDF, where the target surface emerges as the interface between distinct regions. We begin by computing a two-signed local field to distinguish the two sides of manifold patches, and then extend this to a multi-labeled global field capable of separating all sides of a non-manifold structure. By combining this multi-labeled field with the input UDF, we construct material interfaces that support non-manifold mesh extraction via a multi-labeled Marching Cubes algorithm. Extensive experiments on UDFs generated from diverse data sources, including point cloud reconstruction, multi-view reconstruction, and medial axis transforms, demonstrate that our approach robustly handles complex non-manifold surfaces and significantly outperforms existing methods. The source code is available at https://github.com/jjjkkyz/MIND.

Orienting point clouds is a fundamental problem in computer graphics and 3D vision, with applications in reconstruction, segmentation, and analysis. While significant progress has been made, existing approaches mainly focus on watertight, object-level 3D models. The orientation of large-scale, non-watertight 3D scenes remains an underexplored challenge. To address this gap, we propose DACPO (Divide-And-Conquer Point Orientation), a novel framework that leverages a divide-and-conquer strategy for scalable and robust point cloud orientation. Rather than attempting to orient an unbounded scene at once, DACPO segments the input point cloud into smaller, manageable blocks, processes each block independently, and integrates the results through a global optimization stage. For each block, we introduce a two-step process: estimating initial normal orientations by a randomized greedy method and refining them by an adapted iterative Poisson surface reconstruction. To achieve consistency across blocks, we model inter-block relationships using an an undirected graph, where nodes represent blocks and edges connect spatially adjacent blocks. To reliably evaluate orientation consistency between adjacent blocks, we introduce the concept of the visible connected region , which defines the region over which visibility-based assessments are performed. The global integration is then formulated as a 0-1 integer-constrained optimization problem, with block flip states as binary variables. Despite the combinatorial nature of the problem, DACPO remains scalable by limiting the number of blocks (typically a few hundred for 3D scenes) involved in the optimization. Experiments on benchmark datasets demonstrate DACPO's strong performance, particularly in challenging large-scale, non-watertight scenarios where existing methods often fail. The source code is available at https://github.com/zd-lee/DACPO.

Reconstructing CSG trees from CAD models is a critical subject in reverse engineering. While there have been notable advancements in CSG reconstruction, challenges persist in capturing geometric details and achieving efficiency. Additionally, since non-axis-aligned volumetric primitives cannot maintain coplanar characteristics due to discretization errors, existing Boolean operations often lead to zero-volume surfaces and suffer from topological errors during the CSG modeling process. To address these issues, we propose a novel workflow to achieve fast CSG reconstruction and reliable forward modeling. First, we employ feature removal and model subdivision techniques to decompose models into sub-components. This significantly expedites the reconstruction by simplifying the complexity of the models. Then, we introduce a more reasonable method for primitive generation and filtering, and utilize a size-related optimization approach to reconstruct CSG trees. By re-adding features as additional nodes in the CSG trees, our method not only preserves intricate details but also ensures the conciseness, semantic integrity, and editability of the resulting CSG tree. Finally, we develop a coplanar primitive discretization method that represents primitives as large planes and extracts the original triangles after intersection. We extend the classification of triangles and incorporate a coplanar-aware Boolean tree assessment technique, allowing us to achieve manifold and watertight modeling results without zero-volume surfaces, even in extreme degenerate cases. We demonstrate the superiority of our method over state-of-the-art approaches. Moreover, the reconstructed CSG trees generated by our method contain extensive semantic information, enabling diverse model editing tasks.

Unsigned distance fields (UDFs) provide a flexible representation for models with complex topologies, but accurately extracting their zero level sets remains challenging, particularly in preserving topological correctness and fine geometric details. We present DCUDF2, an enhanced method that builds upon DCUDF to address these limitations. Our approach introduces an accuracy-aware loss function with self-adaptive weights, enabling precise geometric fitting while avoiding over-smoothing. To improve robustness, we propose a topology correction strategy that reduces the sensitivity to hyper-parameter settings. Furthermore, we develop new operations leveraging self-adaptive weights to accelerate convergence and improve runtime efficiency. Extensive experiments on diverse datasets demonstrate that DCUDF2 consistently outperforms DCUDF and existing methods in both geometric fidelity and topological accuracy.

Fast detection of exact point-to-point geodesic paths on meshes is still challenging with existing methods. For this, we present a method to reduce the region to be investigated on the mesh for efficiency. It is by our observation that a mesh and its simplified one are very alike so that the geodesic path between two defined points on the mesh and the geodesic path between their corresponding two points on the simplified mesh are very near to each other in the 3D Euclidean space. Thus, with the geodesic path on the simplified mesh, we can generate a region on the original mesh that contains the geodesic path on the mesh, called the search region, by which existing methods can reduce the search scope in detecting geodesic paths, and so obtaining acceleration. We demonstrate the rationale behind our proposed method. Experimental results show that we can promote existing methods well, e.g., the global exact method VTP (vertex-oriented triangle propagation) can be sped up by even over 200 times when handling large meshes. Our search region can also speed up path initialization using the Dijkstra algorithm to promote local methods, e.g., obtaining an acceleration of at least two times in our tests.

In boundary representation (B-rep) reconstruction for computer aided design (CAD) applications, it is still challenging with existing methods to distinguish primitives in the smoothly blended regions reasonably. Thus, intensive manual post-processing is always required for correcting the primitives and their neighboring relationships to obtain a valid B-rep solid, seriously preventing the efficiency. In this paper, we address these challenges by presenting two novel techniques. The first is to robustly extract primitives by iteratively estimating the probability distribution of the noise to eliminate outliers. The second is to present intersection-aware constraints, like tangency and collinearity constraints, to correctly obtain intersections between primitives, which have not been explored in existing methods to our knowledge. Therefore, we can effectively extract primitives, especially those blended smoothly, and obtain high-quality relationships between them. As a result, a valid B-rep model can be constructed without a lot of manual post-processing on topology correction, while not with existing methods. As a benefit, with our constructed B-rep models, their corresponding meshes can be intuitively and conveniently edited, which is quite useful in CAD applications. Experimental results show that our proposed B-rep construction method outperforms both classical and recent learning-based methods in terms of reconstruction efficiency and accuracy.

Recently, building on the foundation of neural radiance field, various techniques have emerged to learn unsigned distance fields (UDF) to reconstruct 3D non-watertight models from multi-view images. Yet, a central challenge in UDF-based volume rendering is formulating a proper way to convert unsigned distance values into volume density, ensuring that the resulting weight function remains unbiased and sensitive to occlusions. Falling short on these requirements often results in incorrect topology or large reconstruction errors in resulting models. This paper addresses this challenge by presenting a novel two-stage algorithm, 2S-UDF, for learning a high-quality UDF from multi-view images. Initially, the method applies an easily trainable density function that, while slightly biased and transparent, aids in coarse reconstruction. The subsequent stage then refines the geometry and appearance of the object to achieve a high-quality reconstruction by directly adjusting the weight function used in volume rendering to ensure that it is unbiased and occlusion-aware. Decoupling density and weight in two stages makes our training stable and robust, distinguishing our technique from existing UDF learning approaches. Evaluations on the DeepFashion3D, DTU, and BlendedMVS datasets validate the robustness and effectiveness of our proposed approach. In both quantitative metrics and visual quality, the results indicate our superior performance over other UDF learning techniques in reconstructing 3D non-watertight models from multi-view images. Our code is available at https://bitbucket.org/jkdeng/2sudf/.

Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces $\alpha$-NeuS$\textemdash$an extension of NeuS$\textemdash$that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https://github.com/728388808/alpha-NeuS.

Abstract It is still challenging with existing methods to distinguish structures from texture details, and so preventing texture filtering. Considering that the textures on both sides of a structural edge always differ much from each other in appearances, we determine whether a pixel is on a structure edge by exploiting the appearance contrast between patches around the pixel, and further propose an efficient implementation method. We demonstrate that our proposed method is more effective than existing methods to distinguish structures from texture details, and our required patches for texture measurement can be smaller than the used patches in existing methods by at least half. Thus, we can improve texture filtering on both quality and efficiency, as shown by the experimental results, e.g., we can handle the textured images with a resolution of 800 × 600 pixels in real‐time. (The code is available at https://github.com/hefengxiyulu/MLPC )

Point-in-spherical-polygon tests are a fundamental problem in computational geometry.For such tests, efficiency is much required for many global information processing matters, especially their real-time processing.Though many efforts have been made, it is still challenging due to the constraints from the non-Euclidean space of the sphere.Recently, a method is proposed to construct an Adaptive Hexagonal Hierarchical Grid (AHHG) to manage spherical polygon edges, by which the non-Euclidean space constraint of the sphere can be well handled to improve point-in-spherical-polygon tests.However, this method is very expensive in the construction of AHHGs, which prevents its use in practice.In this paper, we present novel measures to divide the task of AHHG construction into several subtasks to solve the problems that arise in the parallel construction of incongruent adaptive hierarchies, so we can exploit the parallel computing potential of GPUs for acceleration.We also develop measures to adaptively optimize the hierarchical levels of an AHHG for high efficiency.Experimental results show that we can answer 1,000,000 query points against dynamically varying spherical polygons in over 100,000 edges in real time on a personnel computer, where AHHGs for spherical polygons are individually constructed.This is much superior to the existing methods.

Abstract It is a hot topic to extract road maps from satellite images. However, it is still very challenging with existing methods to achieve high‐quality results, because the regions covered by satellite images are very large and the roads are slender, complex and only take up a small part of a satellite image, making it difficult to distinguish roads from the background in satellite images. In this article, we address this challenge by presenting two modules to more effectively learn road features, and so improving road extraction. The first module exploits the differences between the patches containing roads and the patches containing no road to exclude the background regions as many as possible, by which the small part containing roads can be more specifically investigated for improvement. The second module enhances feature alignment in decoding feature maps by using strip convolution in combination with the attention mechanism. These two modules can be easily integrated into the networks of existing learning methods for improvement. Experimental results show that our modules can help existing methods to achieve high‐quality results, superior to the state‐of‐the‐art methods.

Tensile instability is one of the major obstacles to particle methods in fluid simulation, which would cause particles to clump in pairs under tension and prevent fluid simulation to generate small-scale thin features. To address this issue, previous particle methods either use a background pressure or a finite difference scheme to alleviate the particle clustering artifacts, yet still fail to produce small-scale thin features in free-surface flows. In this article, we propose a dual-particle approach for simulating incompressible fluids. Our approach involves incorporating supplementary virtual particles designed to capture and store particle pressures. These pressure samples undergo systematic redistribution at each time step, grounded in the initial positions of the fluid particles. By doing so, we effectively reduce tensile instability in standard SPH by narrowing down the unstable regions for particles experiencing tensile stress. As a result, we can accurately simulate free-surface flows with rich small-scale thin features, such as droplets, streamlines, and sheets, as demonstrated by experimental results.

Abstract Poisson's equation is one of the most popular partial differential equation (PDE), which is widely used in image processing, computer graphics and other fields. However, solving a large‐scale Poisson's equation always costs huge computational resources. Fast Fourier transform (FFT) is an efficient Poisson solver but it only works in rectangular domain. In this paper, we propose a FFT‐based Poisson solver in nonrectangular domain on regular grids combined with algebraic multigrid (AMG). We extend the original Poisson's equation to a rectangular domain to construct an equivalent equation, so that it can use FFT algorithm to accelerate the solving to Poisson's equation. Experiments show that the FFT‐based Poisson solver can improve the solving speed of large‐scale Poisson's equations in nonrectangular domain. We demonstrate the solver in applications of image processing and fluid simulation.

In this paper, we propose a new method, called DoubleCoverUDF, for extracting the zero level-set from unsigned distance fields (UDFs). DoubleCoverUDF takes a learned UDF and a user-specified parameter r (a small positive real number) as input and extracts an iso-surface with an iso-value r using the conventional marching cubes algorithm. We show that the computed iso-surface is the boundary of the r -offset volume of the target zero level-set S , which is an orientable manifold, regardless of the topology of S. Next, the algorithm computes a covering map to project the boundary mesh onto S , preserving the mesh's topology and avoiding folding. If S is an orientable manifold surface, our algorithm separates the double-layered mesh into a single layer using a robust minimum-cut post-processing step. Otherwise, it keeps the double-layered mesh as the output. We validate our algorithm by reconstructing 3D surfaces of open models and demonstrate its efficacy and effectiveness on synthetic models and benchmark datasets. Our experimental results confirm that our method is robust and produces meshes with better quality in terms of both visual evaluation and quantitative measures than existing UDF-based methods. The source code is available at https://github.com/jjjkkyz/DCUDF.

Extracting concise 3D curve skeletons with existing methods is still a serious challenge as these methods require tedious parameter adjustment to suppress the influence of shape boundary perturbations to avoid spurious branches. In this paper, we address this challenge by enhancing the capture of prominent features and using them for skeleton extraction, motivated by the observation that the shape is mainly represented by prominent features. Our method takes the medial mesh of the shape as input, which can maintain the shape topology well. We develop a series of novel measures for simplifying and contracting the medial mesh to capture prominent features and represent them concisely, by which means the influences of shape boundary perturbations on skeleton extraction are suppressed and the quantity of data needed for skeleton extraction is significantly reduced. As a result, we can robustly and concisely extract the curve skeleton based on prominent features, avoiding the trouble of tuning parameters and saving computations, as shown by experimental results.

For Reeb graph extraction on surfaces, existing methods always use the isolines of a function defined on the surface to detect the surface components and the neighboring relationships between them. Since such detection is unstable, it is still a challenge for the extracted Reeb graphs to stably and concisely encode the topological information of the surface. In this article, we address this challenge by using foliation leaves to extract Reeb graphs. In particular, we employ a method for generating measured harmonic foliations by defining loops for foliation initialization and diffusing leaves from loops over the surface. We demonstrate that when the loops are determined, the neighboring relationships between the leaves from different loops are fixed. Thus, we can use loops to represent surface components for robustly detecting the interrelationships between surface components. As a result, we are able to extract stable and concise Reeb graphs. We developed novel measures for loop determination and improved foliation generation, and our method allows the user to manually prescribe loops for generating Reeb graphs with desired structures. Therefore, the potential of Reeb graphs for representing surfaces is enhanced, including conveniently representing the symmetries of the surface and ignoring topological noise. This is verified by our experimental results which indicate that our Reeb graphs are compact and expressive, promoting shape analysis.

Poisson surface reconstruction (PSR) remains a popular technique for reconstructing watertight surfaces from 3D point samples thanks to its efficiency, simplicity, and robustness. Yet, the existing PSR method and subsequent variants work only for oriented points. This paper intends to validate that an improved PSR, called iPSR, can completely eliminate the requirement of point normals and proceed in an iterative manner. In each iteration, iPSR takes as input point samples with normals directly computed from the surface obtained in the preceding iteration, and then generates a new surface with better quality. Extensive quantitative evaluation confirms that the new iPSR algorithm converges in 5--30 iterations even with randomly initialized normals. If initialized with a simple visibility based heuristic, iPSR can further reduce the number of iterations. We conduct comprehensive comparisons with PSR and other powerful implicit-function based methods. Finally, we confirm iPSR's effectiveness and scalability on the AIM@SHAPE dataset and challenging (indoor and outdoor) scenes. Code and data for this paper are at https://github.com/houfei0801/ipsr.

Existing methods for extracting 3D curve skeletons mostly suffer from the difficulty of finding the center points of 3D shapes and tedious manual adjustments of the thresholds for pruning spurious branches due to the influence of shape boundary perturbations. In this article, we present a method based on medial surfaces of 3D shapes for the convenient and fast extraction of high-quality curve skeletons. Our main contribution is a simple and stable centeredness measure. It is based on simulating fire propagation via the scheme of inside-out evolution from the interior to the boundary, differentiating it from existing methods that use the scheme of outside-in evolution from the boundary to the interior. Thus, our measure is much more localized, and it can be implemented with a high degree of parallelism. In addition, we propose measures to effectively suppress the influence of details to obtain a stable measurement, and employ minimum set covers to optimize the center points to generate compact skeletons, which enables spurious branches to be effectively excluded without the tedious work of manually adjusting thresholds. Our experiments show the superiority of our method over existing methods, including its convenient generation of clean, compact and centered curve skeletons while running much faster than state-of-the-art methods.

In simulating viscous incompressible SPH fluids, incompressibility and viscosity are typically solved in two separate stages. However, the interference between pressure and shear forces could cause the missing of behaviors that include preservation of sharp surface details and remarkable viscous behaviors such as buckling and rope coiling. To alleviate this problem, we introduce for the first time the semi-implicit method for pressure linked equations (SIMPLE) into SPH to solve incompressible fluids with a broad range viscosity. We propose to link incompressibility and viscosity solvers, and impose incompressibility and viscosity constraints iteratively to gradually remove the interference between pressure and shear forces. We will also discuss how to solve the particle deficiency problem for both incompressibility and viscosity solvers. Our method is stable at simulating incompressible fluids whose viscosity can range from zero to an extremely high value. Compared to state-of-the-art methods, our method not only produces realistic viscous behaviors, but is also better at preserving sharp surface details.

The grid-based approach is popular for point-in-polygon tests. However, there is a trade-off between the preprocessing and the inclusion test, which always requires the grid resolutions to be tuned. In this article, we address this challenge by enhancing the grid structure using y-axis-aligned stripes, which are formed by the y-axis-aligned lines passing through the endpoints of the edge segments in the cell, thereby managing the edge segments in each grid cell. Moreover, we precompute the inclusion properties of the x-axis-aligned top borders of the stripes during preprocessing. Therefore, to answer a query point with the ray crossing method, we can emit a ray from the point to propagate upwards until the ray arrives at the top border of a stripe. We thoroughly consider singular cases to guarantee each query point can be answered in the stripe that contains the point. In our method, the computational load can be decreased, as one coordinate of the intersection point between the ray and an edge is known in advance, and parallel computing can be well exploited because the branching operations for determining whether an edge intersects with the ray are saved. Experimental results show that the efficiency of our method does not vary much with respect to the grid resolutions, so the trouble of tuning grid resolutions can be avoided. Ultimately, our method with a low grid resolution can reduce the preprocessing time and still achieve a higher inclusion test efficiency than the existing methods with a high grid resolution, especially on GPUs.

We propose an algorithm to compute global conformal parameterizations of high-genus meshes, which is based on an implementation of holomorphic quadratic differentials. First, we design a novel diffusion method which is capable of computing a pole-free discrete harmonic measured foliation. Second, we propose a definition for discrete holomorphic quadratic differential which consists of a horizontal and a vertical harmonic measured foliation. Third, we present a practical algorithm to approximate the discrete natural coordinates for a holomorphic quadratic differential, which represents a flat metric with cones conformal to the original metric, i.e., a parameterization. Finally, we apply the discrete natural coordinates for parameterization of high genus meshes. Our parameterization method is global conformal and simple to implement. The advantage of our method over the approach based on holomorphic differential one-forms is that ours has a larger space of parameterizations. We demonstrate our approach with hundreds of configurations on dozens of meshes to show its robustness on conformal parameterization.

Abstract Superpixel segmentation is important for promoting various image processing tasks. However, existing methods still have difficulties in generating high‐quality superpixels in textured images, because they cannot separate textures from structures well. Though texture filtering can be adopted for smoothing textures before superpixel segmentation, the filtering would also smooth the object boundaries, and thus weaken the quality of generated superpixels. In this paper, we propose to use the adaptive scale box smoothing instead of the texture filtering to obtain more high‐quality texture and boundary information. Based on this, we design a novel distance metric to measure the distance between different pixels, which considers boundary, color and Euclidean distance simultaneously. As a result, our method can achieve high‐quality superpixel segmentation in textured images without texture filtering. The experimental results demonstrate the superiority of our method over existing methods, even the learning‐based methods. Benefited from using boundaries to guide superpixel segmentation, our method can also suppress noise to generate high‐quality superpixels in non‐textured images.

This work proposed a semi-supervised method for automatic texture filtering. Our method leveraged a limited amount of labeled data and a large amount of unlabeled data to train Generative Adversarial Networks (GANs). Separate loss functions were designed for both labeled and unlabeled datasets. Our main contribution is the introduction of knowledge extracted from shallow and deep layers in neural networks. Loss defined within shallow layers preserves the edge, while loss defined within the deep layers identifies the semantic content and conversely removes the small-scale texture variations. This contribution directly addresses the major challenge for texture filtering, distinguishing the structural content from non-structural textures at the pixel level. The extracted information, in our study, improved the content and color consistency before and after the process of filtering, for unlabeled samples in particular. The proposed method offers twofold benefits: first, significant reductions in the amounts of time and effort expended in reconstructing the labeled dataset, especially given the delicate operations required at the pixel level; second, a reduction in over-fitting, in supervised learning with a small amount of labeled data, by utilizing a large amount of unlabeled data. The results confirm that our method can perform comparably with non-learning-based methods, alleviating the demand for the determination of optimal parameter values.

Abstract Image composition extracts the content of interest (COI) from a source image and blends it into a target image to generate a new image. In the majority of existing works, the COI is manually extracted and then overlaid on top of the target image. However, in practice, it is often necessary to deal with situations in which the COI is partially occluded by the target image content. In this regard, both tasks of extracting the COI and cropping its occluded part require intensive user interactions, which are laborious and seriously reduce the composition efficiency. This paper addresses the aforementioned challenges by proposing an efficient image composition method. First, we extract the semantic contents of the images by using state‐of‐the‐art deep learning methods. Therefore, the COI can be selected with clicks only, which can greatly reduce the demanded user interactions. Second, according to the user's operations (such as translation or scale) on the COI, we can effectively infer the occlusion relationships between the COI and the contents of the target image. Thus, the COI can be adaptively embedded into the target image without concern about cropping its occluded part. Therefore, the procedures of content extraction and occlusion handling can be significantly simplified, and work efficiency is remarkably improved. Experimental results show that compared to existing works, our method can reduce the number of user interactions to approximately one‐tenth and increase the speed of image composition by more than ten times.

Abstract The existing methods for intrinsic symmetry detection on 3D models always need complex measures such as geodesic distances for describing intrinsic geometry and statistical computation for finding non‐rigid transformations to associate symmetrical shapes. They are expensive, may miss symmetries, and cannot guarantee their obtained symmetrical parts in high quality. We observe that only extrinsic symmetries exist between convex shapes, and two intrinsically symmetric shapes can be determined if their belonged convex sub‐shapes are symmetrical to each other correspondingly and connected in a similar topological structure. Thus, we propose to decompose the model into convex parts, and use the similar structures of the skeleton of the model to guide combination of extrinsic symmetries between convex parts for intrinsic symmetry detection. In this way, we give up statistical computation for intrinsic symmetry detection, and avoid complex measures for describing intrinsic geometry. With the similar structures being from small to large gradually, we can quickly detect multi‐scale partial intrinsic symmetries in a bottom up manner. Benefited from the well segmented convex parts, our obtained symmetrical parts are in high quality. Experimental results show that our method can find many more symmetries and runs much faster than the existing methods, even by several orders of magnitude.

Texture filtering seeks to smooth out textured details in order to present structures prominently. To filter out multi-scale textured details while preserving structures, some methods propose to adjust the size of the filtering windows by handling the pixels near structures with small windows and the other pixels with large windows. Unfortunately, their adjustment measures are not very effective in treating complex situations. They may handle the pixels inside small structures with large windows, which overly smooths them, or they may be incapable of smoothing out large-scale textures. With regard to this, in this paper, we present a novel method that adjusts the window size for a pixel by checking similar pixels in its neighborhood. In general, pixels nearer structures have fewer similar pixels in their neighborhoods than the pixels that are farther away from structures. Thus, our adjustment can adaptively adjust window sizes by the distances from pixels to structures, which improves the potential to treat complex situations. The experimental results show that we can well filter out very large-scale textures while preserving small structures with high quality in a manner superior to the state-of-the-art methods. In addition, our method is very simple and efficient, and can be used easily in applications.

Recommendation is essential to many online services; however current systems often provide limited interaction and visualization mechanisms, affecting the user satisfaction of recommendation. This paper presents an interactive recommendation approach for the general public without any knowledge of recommendation or visualization algorithms. Our approach emphasizes interactivity, explicit user input, and semantic information convey with the following two components. First, we propose a Latent Semantic Model that captures the statistical features of semantic concepts on 2D domains and abstracts user preferences for personal recommendation, so that high-dimensional spectral space from the rating records can be understood and interacted with directly. Second, we propose an interactive recommendation approach through a storytelling mechanism for promoting the communication between the user and the recommendation system. We demonstrate and evaluate our approach with a real dataset. Our approach can also be extended to other applications including various online recommendation systems.

This paper proposes a novel method for decorating 3D surfaces using a new type of vector graphics, called Poisson Vector Graphics (PVG). Unlike other existing techniques that frequently require local/global parameterization, our approach advocates a parameterization-free paradigm, affording decoration of geometric models with any topological type while minimizing the overall computational expenses. Since PVG supports a set of simple discrete curves, it is straightforward for users to edit colors and synthesize geometry details. Meanwhile, the details could be organized by Poisson Region (PR), leading to much smoother decoration than those of Diffusion Curve (DC). Consequently, it is an ideal tool to create smooth relief. It may be noted that, DC is adequate to create sharp or discontinuous results. But PR is superior to DC, supporting level-of-details editing on meshes thanks to its smoothness. To render PVG on meshes efficiently, we develop a Poisson solver based on harmonic B-splines, which could be constructed using geodesic Voronoi diagram . Our Poisson solver is a local solver for rendering with more flexibility and versatility. We demonstrate the efficacy of our approach on synthetic and real-world 3D models.

Texture filtering depends on high-quality texture measurement to separate structures from textures. However, the existing methods employ axis-aligned box windows for texture measurement, which may cover different texture regions, and so lowering the measurement quality because structure edges are not always parallel to the axes. Additionally, the existing texture measurements consider intensity contrast at the pixel level and do not account for the linear characteristics of structure edges in filtering windows; thus, their measurement effectiveness is limited. This results in a dilemma for texture filtering. Large-scale textures are not smoothed using smaller windows, while small structures are removed using larger windows. In this paper, we present edge-aware measures to improve texture measurement. Edge-aware windows are constructed such that each window is inside a texture region to the greatest extent possible, and the linear characteristics of structure edges are accounted for in the texture measurement. Furthermore, we use large box windows for texture filtering and long and narrow edge-aware small windows for texture measurement to filter out large-scale textures while preserving small structures. The experimental results show improved texture filtering with our method compared with existing methods.

Existing matting methods focus on improving matte quality to produce high-quality composites. This generally requires significant manual interaction, a tedious task for the user. Despite these efforts, the composites may still exhibit evident artifacts, especially in the case of transparent and complicated objects as their related pixels always contain percentage of the background. In this paper, we focus on the enhanced use of mattes to produce satisfactory composites by suppressing the discrepancies around objects of interest. This approach is motivated by cloning methods but overcomes their shortcoming of ineffective treatment of the over-included regions around objects of interest. For this, we present an enhanced matting function by including a term to smooth the local contrasts for seamless composition, and meanwhile, we develop a novel algorithm to generate mattes with reduced user interaction and improved usability. As a result, we reduce the composite's dependence on the user's input and only require the user to drag a box to enclose the objects of interest. As shown in the user studies and the experimental results, our method requires many times less user interaction than the existing matting methods and cloning methods. Our method is more effective in producing good composites in a simple interactive manner, especially when treating transparent and complicated objects, thereby providing a superior approach for image composition.

In propagating edits for image editing, some edits are intended to affect limited local regions, while others act globally over the entire image. However, the ambiguity problem in propagating edits is not adequately addressed in existing methods. Thus, tedious user input requirements remain since the user must densely or repeatedly input control samples to suppress ambiguity. In this paper, we address this challenge to propagate edits suitably by marking edits for local or global propagation and determining their reasonable propagation scopes automatically. Thus, our approach avoids propagation conflicts, effectively resolving the ambiguity problem. With the reduction of ambiguity, our method allows fewer and less-precise control samples than existing methods. Furthermore, we provide a uniform framework to propagate local and global edits simultaneously, helping the user to quickly obtain the intended results with reduced labor. With our unified framework, the potentially ambiguous interaction between local and global edits (evident in existing methods that propagate these two edit types in series) is resolved. We experimentally demonstrate the effectiveness of our method compared with existing methods.

Gradient domain methods are popular for image processing. However, these methods even the edge-preserving ones cannot preserve edges well in some cases. In this paper, we present new constraints explicitly to better preserve edges for general gradient domain image filtering and theoretically analyse why these constraints are edge-aware. Our edge-aware constraints are easy to implement, fast to compute and can be seamlessly integrated into the general gradient domain optimization framework. The improved framework can better preserve edges while maintaining similar image filtering effects as the original image filters. We also demonstrate the strength of our edge-aware constraints on various applications such as image smoothing, image colorization and Poisson image cloning.

Abstract Natural‐looking insect animation is very difficult to simulate. The fast movement and small scale of insects often challenge the standard motion capture techniques. As for the manual key‐framing or physics‐driven methods, significant amounts of time and efforts are necessary due to the delicate structure of the insect, which prevents practical applications. In this paper, we address this challenge by presenting a two‐level control framework to efficiently automate the modeling and authoring of insects’ locomotion. On the top level, we design a Triangle Placement Engine to automatically determine the location and orientation of insects’ foot contacts, given the user‐defined trajectory and settings, including speed, load, path and terrain etc. On the low‐level, we relate the Central Pattern Generator to the triangle profiles with the assistance of a Controller Look‐Up Table to fast simulate the physically‐based movement of insects. With our approach, animators can directly author insects’ behavior among a wide range of locomotion repertoire, including walking along a specified path or on an uneven terrain, dynamically adjusting to external perturbations and collectively transporting prey back to the nest.

It is very important to extract high quality texture features from images. This is, however, often laborious, because the randomness in the color distribution patterns for texture elements makes texture measurement very difficult, despite these elements having a very similar visual appearance. In this paper, we propose the use of multi-scale color histograms to measure the effect of color distribution patterns efficiently and without having to compute the actual patterns, which saves considerable effort. Meanwhile, the hue-saturation-intensity color model is mainly adopted to take the advantage of human visual experiences in texture recognition. We discuss and validate the effectiveness and efficiency of our method by applying to various benchmarks. The results show that we can extract quality dominant textures automatically in real time, and faster by several orders of magnitude than existing methods.

Rendering multifragment effects using graphics processing units (GPUs) is attractive for high speed. However, the efficiency is seriously compromised, because ordering fragments on GPUs is not easy and the GPU's memory may not be large enough to store the whole scene geometry. Hitherto, existing methods have been unsuitable for large models or have required many passes for data transmission from CPU to GPU, resulting in a bottleneck for speedup. This paper presents a stream method for accurate rendering of multifragment effects. It decomposes the model into parts and manages these in an efficient manner, guaranteeing that the parts can easily be ordered with respect to any viewpoint, and that each part can be rendered correctly on the GPU. Thus, we can transmit the model data part by part, and once a part has been loaded onto the GPU, we immediately render it and composite its result with the results of the processed parts. In this way, we need only a single pass for data access with a very low bounded memory requirement. Moreover, we treat parts in packs for further acceleration. Results show that our method is much faster than existing methods and can easily handle large models of any size.

Abstract It is popular to edit the appearance of images using strokes, owing to their ease of use and convenience of conveying the user's intention. However, propagating the user inputs to the rest of the images requires solving an enormous optimization problem, which is very time consuming, thus preventing its practical use. In this paper, a two‐step edit propagation scheme is proposed, first to solve edits on clusters of similar pixels and then to interpolate individual pixel edits from cluster edits. The key in our scheme is that we use efficient stroke sampling to compute the affinity between image pixels and strokes. Based on this, our clustering does not need to be stroke‐adaptive and thus the number of clusters is greatly reduced, resulting in a significant speedup. The proposed method has been tested on various images, and the results show that it is more than one order of magnitude faster than existing methods, while still achieving precise results compared with the ground truth. Moreover, its efficiency is not sensitive to the number of strokes, making it suitable for performing dense edits in practice.

The ubiquity of symmetry in nature and man-made artifacts has made symmetry discovery an important tool for numerous applications. The most fundamental and visually prominent kind of symmetry is partial rigid symmetry, which is explained as the invariance between parts of a 3D model under a set of translation, rotation, reflection, and uniform scaling generators. Thus automatic discovery of partial rigid symmetry on general 3D models, with no assumption on the size, shape or location of the symmetric parts, keeps to be a hot topic during recent years. Among such kind of works, the transformation voting technique [Mitra et al. 2006] is most widely used, due to its high efficiency and easiness for understanding and implementation.

We propose a new compression algorithm for massive models, which consist of a large number of small to medium sized connected components. It is by efficiently exploiting repetitive patterns in the input model. Compared with the similar work by finding repetitive patterns, our new algorithm is more efficient on detecting repeated components by recognizing instances repeating in various scalings. We also propose an efficient compression scheme for transformation data. As a result, it can achieve a considerably higher compression ratio.

This paper presents the layer-based representation of polyhedrons and its use for point-in-polyhedron tests. In the representation, the facets and edges of a polyhedron are sequentially arranged, and so, the binary search algorithm is efficiently used to speed up inclusion tests. In comparison with conventional representation for polyhedrons, the layer-based representation we propose greatly reduces the storage requirement because it represents much information implicitly, though it still has a storage complexity O(n). It is simple to implement, and robust for inclusion tests because many singularities are erased in constructing the layer-based representation. By incorporating an octree structure for organizing polyhedrons, our approach can run at a speed comparable with Binary Space Partitioning (BSP)-based inclusion tests, and at the same time greatly reduce storage and preprocessing time in treating large polyhedrons. We have developed an efficient solution for point-in-polyhedron tests with the time complexity varying between O(n) and O(logn), depending on the polyhedron shape and the constructed representation, and less than O(log3n) in most cases. The time complexity of preprocess is between O(n) and O(n2), varying with polyhedrons, where n is the edge number of a polyhedron.

Most of existing importance sampling methods for direct illumination exploit importance of illumination and surface BRDF. Without taking the visibility into consideration, they can not adaptively adjust the number of samples for each pixel during the sampling process. As a result, these methods tend to produce images with noise in partially occluded regions. In this paper, we introduce an incremental wavelet importance sampling approach, in which the visibility information is used to determine the number of samples at run time. For this purpose, we present a perceptual-based variance that is computed from visibility of samples. In the sampling process, the Halton sample points are incrementally warped for each pixel until the variance of warped samples converges. We demonstrate that our method is more efficient than existing importance sampling approaches.

This paper presents a novel scheme for accelerating ray traversal computation in ray tracing. By the scheme, a pre-computed stage is applied to constructing what is called a traversal field for each rigid object that records the destinations for all possible incoming rays. The field data, which could be efficiently compressed offline, is stored in a small number of big rectangles called ray-relays that enclose each approximate convex segment of an object. In the ray-tracing stage, the records on relays are retrieved in a constant time, so that a ray traversal is implemented as a simple texture lookup on GPU. Thus, the performance of our approach is only related to the number of relays rather than scene size, while the number of relays is quite small. In addition, because the traversal fields only depend on the internal construction of each convex segment, they can be used to ray trace objects undergoing rigid motions at a negligible extra cost. Experimental results show that interactive rates could be achieved for dynamic scenes with the effects of specular reflections and refractions on an ordinary desk PC with GPU.

By employment of a footprint table in conducting intensity integration, splatting method has been very successful in rendering regular data volumes. Recently, the method has also been extended to render irregular data volumes. However, since samples in irregular volumes vary greatly in size and shape, the footprint table is unable to be employed in an efficient manner. This hinders the application of splatting approach from being used in the irregular volume case. In this paper, an adaptable splatting method is proposed, which provides an efficient way to integrate color intensity in terms of footprint table for the samples in various sizes. Experiments show that the new method may be used to produce better images without extra expense.

Selective visualization is a solution for visualizing data of large size and dimensionality. In this paper a new method is proposed for effectively rendering certain chosen parts among the full set of data in terms of a colour buffer, referred to as the virtual plane, for storing intermediate results. By this method, scientists may concentrate their attention on the contents of data in which they are interested. Besides, the method could be easily integrated with all the current direct volume rendering techniques, especially progressive refinement methods and selective methods. Copyright © 1999 John Wiley & Sons, Ltd.