Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic consistency. Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors. Inspired by human design cognition, we present CasLayout, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages with explicit physical and semantic roles: (1) predicting furniture quantity and categories, (2) refining object sizes and feature embeddings, (3) modeling spatial relationships in a latent space, and (4) generating Oriented Bounding Boxes (OBBs). This decoupled architecture reduces data requirements and enables flexible integration of Large Language Models (LLMs) and Vision Language Models (VLMs) for zero-shot tasks such as image-to-scene generation. To maintain physical validity within complex floor plans, we explicitly model building elements ( e.g. , walls, doors, and windows) as conditional constraints. Furthermore, to address the high entropy of dense relation graphs, we introduce a sparse relation graph formulation aligned with human spatial descriptions. By encoding these sparse graphs into a compact latent space using a bidirectional Variational Autoencoder (VAE), the proposed framework provides enhanced relational controllability, allowing generated layouts to better respect functional organization. Experiments demonstrate that CasLayout achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.

Point cloud normal estimation is a fundamental task in 3D geometry processing, playing a crucial role in applications such as 3D reconstruction, object recognition, and surface analysis. While recent learning-based methods achieve notable advancements in normal prediction, they often overlook the critical aspect of equivariance. This oversight leads to inefficient learning of symmetric patterns inherent in geometric data. To address this issue, we propose E$^{3}$3-Net, an innovative neural network architecture designed to inherently achieve equivariance for normal estimation. We introduce an efficient random frame method, which significantly reduces the training resources required for this task to just 1/8 of previous work, while simultaneously enhancing prediction accuracy. Furthermore, we design a Gaussian-weighted loss function and a receptive-aware inference strategy that effectively leverage the local properties of point clouds, ensuring more precise and reliable normal estimation. Our method demonstrates superior performance across both synthetic and real-world datasets, consistently outperforming current state-of-the-art techniques by a substantial margin. Specifically, we achieve a 4% improvement in RMSE on the PCPNet dataset, 2.67% on the SceneNN dataset, and 2.44% on the FamousShape dataset, highlighting the robustness and scalability of E$^{3}$3-Net in diverse environments.

3D Gaussian Splatting (3DGS) has shown remarkable potential in novel view synthesis. However, it still encounters significant challenges in reconstructing dynamic scenes, particularly when dealing with reflective surfaces. To address this issue, we propose a novel 3DGS-based method for dynamic scene reconstruction with explicit reflection modeling. Our approach integrates deferred shading with a dual-environment map that combines static and dynamic components, enabling effective modeling of specular reflections. This allows our method to capture both steady and temporally varying lighting, resulting in more realistic renderings. We evaluate the proposed method on the benchmark dynamic reflection dataset, NERF-DS, and compare it with state-of-the-art approaches. Experimental results show that our method achieves superior or comparable performance in terms of PSNR, SSIM, and LPIPS metrics compared to competing approaches.

Non-rigid alignment of point clouds is crucial for scene understanding, reconstruction, and various computer vision and robotics tasks. Recent advancements in implicit deformation networks for non-rigid registration have significantly reduced the reliance on large amounts of annotated training data. However, existing state-of-the-art methods still face challenges in handling occlusion scenarios. To address this issue, this paper introduces an innovative unsupervised method called Occlusion-Aware Registration (OAR) for non-rigidly aligning point clouds. The key innovation of our method lies in the utilization of the adaptive correntropy function as a localized similarity measure, enabling us to treat individual points distinctly. In contrast to previous approaches that solely minimize overall deviations between two shapes, we combine unsupervised implicit neural representations with the maximum correntropy criterion to optimize the deformation of unoccluded regions. This effectively avoids collapsed, tearing, and other physically implausible results. Moreover, we present a theoretical analysis and establish the relationship between the maximum correntropy criterion and the commonly used Chamfer distance, highlighting that the correntropy-induced metric can be served as a more universal measure for point cloud analysis. Additionally, we introduce locally linear reconstruction to ensure that regions lacking correspondences between shapes still undergo physically natural deformations. Our method achieves superior or competitive performance compared to existing approaches, particularly when dealing with occluded geometries. We also demonstrate the versatility of our method in challenging tasks such as large deformations, shape interpolation, and shape completion under occlusion disturbances.

Filleting is a fundamental operation in CAD systems, akin to a ball rolling between two adjacent surface patches, resulting in a seamless connection. The reverse process, which we refer to as DeFillet in this paper, is crucial for CAE analysis and secondary design phases. However, it presents significant challenges, particularly when the input data originates from surface reconstruction or discretization processes. Our DeFillet algorithm is inspired by the observation that the rolling-ball center defines an osculating sphere, while the Voronoi diagram of surface samples provides sufficiently many rolling-ball center candidates. By leveraging this insight, we compute a transformation between the Voronoi vertices and the surface samples, enabling the efficient identification of fillet regions. Subsequently, we formulate the reconstruction of sharp features as a quadratic optimization problem. Our method's effectiveness has been validated through extensive testing using self-constructed models and 100 filleted models selected from the Fusion 360 Gallery dataset. The code for this paper is publicly available at https://github.com/xiaowuga/DeFillet.

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.

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.

Mesh denoising is a crucial technology that aims to recover a high-fidelity 3D mesh from a noise-corrupted one. Deep learning methods, particularly graph convolutional networks (GCNs) based mesh denoisers, have demonstrated their effectiveness in removing various complex real-world noises while preserving authentic geometry. However, it is still a quite challenging work to faithfully regress uncontaminated normals and vertices on meshes with irregular topology. In this article, we propose a novel pipeline that incorporates two parallel normal-aware and vertex-aware branches to achieve a balance between smoothness and geometric details while maintaining the flexibility of surface topology. We introduce ResGEM, a new GCN, with multi-scale embedding modules and residual decoding structures to facilitate normal regression and vertex modification for mesh denoising. To effectively extract multi-scale surface features while avoiding the loss of topological information caused by graph pooling or coarsening operations, we encode the noisy normal and vertex graphs using four edge-conditioned embedding modules (EEMs) at different scales. This allows us to obtain favorable feature representations with multiple receptive field sizes. Formulating the denoising problem into a residual learning problem, the decoder incorporates residual blocks to accurately predict true normals and vertex offsets from the embedded feature space. Moreover, we propose novel regularization terms in the loss function that enhance the smoothing and generalization ability of our network by imposing constraints on normal fidelity and consistency. Comprehensive experiments have been conducted to demonstrate the superiority of our method over the state-of-the-art on both synthetic and real-scanned datasets.

This work presents an accurate and robust method for estimating normals from point clouds. In contrast to predecessor approaches that minimize the deviations between the annotated and the predicted normals directly, leading to direction inconsistency, we first propose a new metric termed Chamfer Normal Distance to address this issue. This not only mitigates the challenge but also facilitates network training and substantially enhances the network robustness against noise. Subsequently, we devise an innovative architecture that encompasses Multi-scale Local Feature Aggregation and Hierarchical Geometric Information Fusion. This design empowers the network to capture intricate geometric details more effectively and alleviate the ambiguity in scale selection. Extensive experiments demonstrate that our method achieves the state-of-the-art performance on both synthetic and real-world datasets, particularly in scenarios contaminated by noise. Our implementation is available at https://github.com/YingruiWoo/CMG-Net_Pytorch.

This paper presents a novel non-rigid point set registration method that is inspired by unsupervised clustering analysis. Unlike previous approaches that treat the source and target point sets as separate entities, we develop a holistic framework where they are formulated as clustering centroids and clustering members, separately. We then adopt Tikhonov regularization with an$\ell_{1}$-induced Laplacian kernel instead of the commonly used Gaussian kernel to ensure smooth and more robust displacement fields. Our formulation delivers closed-form solutions, theoretical guarantees, independence from dimensions, and the ability to handle large deformations. Subsequently, we introduce a clustering-improved Nyström method to effectively reduce the computational complexity and storage of the Gram matrix to linear, while providing a rigorous bound for the low-rank approximation. Our method achieves high accuracy results across various scenarios and surpasses competitors by a significant margin, particularly on shapes with sub-stantial deformations. Additionally, we demonstrate the versatility of our method in challenging tasks such as shape transfer and medical registration. [Code release]

This work presents a novel and effective method for fitting multidimensional ellipsoids (i.e., ellipsoids embedded in [Formula: see text]) to scattered data in the contamination of noise and outliers. Unlike conventional algebraic or geometric fitting paradigms that assume each measurement point is a noisy version of its nearest point on the ellipsoid, we approach the problem as a Bayesian parameter estimate process and maximize the posterior probability of a certain ellipsoidal solution given the data. We establish a more robust correlation between these points based on the predictive distribution within the Bayesian framework, i.e., considering each model point as a potential source for generating each measurement. Concretely, we incorporate a uniform prior distribution to constrain the search for primitive parameters within an ellipsoidal domain, ensuring ellipsoid-specific results regardless of inputs. We then establish the connection between measurement point and model data via Bayes' rule to enhance the method's robustness against noise. Due to independent of spatial dimensions, the proposed method not only delivers high-quality fittings to challenging elongated ellipsoids but also generalizes well to multidimensional spaces. To address outlier disturbances, often overlooked by previous approaches, we further introduce a uniform distribution on top of the predictive distribution to significantly enhance the algorithm's robustness against outliers. Thanks to the uniform prior, our maximum a posterior probability coincides with a more tractable maximum likelihood estimation problem, which is subsequently solved by a numerically stable Expectation Maximization (EM) framework. Moreover, we introduce an ε-accelerated technique to expedite the convergence of EM considerably. We also investigate the relationship between our algorithm and conventional least-squares-based ones, during which we theoretically prove our method's superior robustness. To the best of our knowledge, this is the first comprehensive method capable of performing multidimensional ellipsoid-specific fitting within the Bayesian optimization paradigm under diverse disturbances. We evaluate it across lower and higher dimensional spaces in the presence of heavy noise, outliers, and substantial variations in axis ratios. Also, we apply it to a wide range of practical applications such as microscopy cell counting, 3D reconstruction, geometric shape approximation, and magnetometer calibration tasks. In all these test contexts, our method consistently delivers flexible, robust, ellipsoid-specific performance, and achieves the state-of-the-art results.

Multiview 3-D reconstruction holds considerable promise across a wide applications in social manufacturing. Conducting in-depth research on precise and robust multiview 3-D reconstruction holds the potential to significantly empower the domain of social manufacturing. Recently, there has been a burgeoning interest in the domain of neural implicit surfaces learning through volume rendering for the purpose of multiview reconstruction without 3-D supervision. Conventional approaches often overlook explicit multiview geometry constraints, resulting in shortcomings in generating consistent surface reconstructions and recovering fine details. To solve this, we propose geometry-guided neural implicit surface (GG-NeuS), a geometry-guided neural implicit surfaces learning method for multiview surface reconstruction. Our model places a stronger emphasis on maintaining geometry consistency, significantly enhancing the quality of reconstruction. First, we enforce multiview geometry constraints on the surface points by locating the zero-level set of signed distance function (SDF). Second, we incorporate normal cues, predicted by general-purpose monocular estimators, to substantially recover fine geometric details. Additionally, we introduce a voxel-based surface reconstruction methodology that strikes an optimal balance between training time and reconstruction quality. Through comprehensive qualitative and quantitative experiments and analyses, we demonstrate thatGG-NeuSsuccessfully reconstructs fine-grained surface details and achieves superior surface reconstruction quality than state-of-the-art approaches.

The registration of unitary-modality geometric data has been successfully explored over past decades. However, existing approaches typically struggle to handle cross-modality data due to the intrinsic difference between different models. To address this problem, in this article, we formulate the cross-modality registration problem as a consistent clustering process. First, we study the structure similarity between different modalities based on an adaptive fuzzy shape clustering, from which a coarse alignment is successfully operated. Then, we optimize the result using fuzzy clustering consistently, in which the source and target models are formulated as clustering memberships and centroids, respectively. This optimization casts new insight into point set registration, and substantially improves the robustness against outliers. Additionally, we investigate the effect of fuzzier in fuzzy clustering on the cross-modality registration problem, from which we theoretically prove that the classical Iterative Closest Point (ICP) algorithm is a special case of our newly defined objective function. Comprehensive experiments and analysis are conducted on both synthetic and real-world cross-modality datasets. Qualitative and quantitative results demonstrate that our method outperforms state-of-the-art approaches with higher accuracy and robustness. Our code is publicly available at https://github.com/zikai1/CrossModReg.

We propose a novel and efficient method for reconstructing manifold surfaces from point clouds. Unlike previous approaches that use dense implicit reconstructions or piecewise approximations and overlook inherent structures like quadrics in CAD models, our method faithfully preserves these quadric structures by assembling primitives. To achieve high-quality primitive extraction, we use a variational shape approximation, followed by a mesh arrangement for space partitioning and candidate primitive patches generation. We then introduce an effective pruning mechanism to classify candidate primitive patches as active or inactive, and further prune inactive patches to reduce the search space and speed up surface extraction significantly. Finally, the optimal active patches are computed by a binary linear programming and assembled as manifold and watertight surfaces. We perform extensive experiments on a wide range of CAD objects to validate its effectiveness.

We present a novel yet effective method for detecting elliptical primitives in cluttered, occluded images, which has versatile applications in computer vision and multimedia processing fields. We begin by the fast extraction of smooth arcs from the edge map, followed by the construction of a directed graph and a disjoint-set forest, whereby the arc relationships are effectively encoded to enhance the arc grouping process. Compared with representative approaches such as the depth-first search, the disjoint-set forest enables complete grouping of arcs to generate candidate ellipses. Moreover, it merely has linear memory complexity and constant access time, hence guarantees fast detection. To boost precision and remove false positives, we propose to project the candidate ellipses onto the original image, to align the gradients of ellipses and the image pixels. We also vectorize the elliptical parameters to depress duplicated candidates. We perform extensive experiments on both synthetic and challenging real-world datasets, to show that our detector is accurate and efficient, as well as versatile in many practical tasks. The source code and datasets are available at https://github.com/xiaowuga/EDSF.

This study presents a high-accuracy, efficient, and physically induced method for 3D point cloud registration, which is the core of many important 3D vision problems. In contrast to existing physics-based methods that merely consider spatial point information and ignore surface geometry, we explore geometry aware rigid-body dynamics to regulate the particle (point) motion, which results in more precise and robust registration. Our proposed method consists of four major modules. First, we leverage the graph signal processing (GSP) framework to define a new signature, i.e., point response intensity for each point, by which we succeed in describing the local surface variation, resampling keypoints, and distinguishing different particles. Then, to address the shortcomings of current physics-based approaches that are sensitive to outliers, we accommodate the defined point response intensity to median absolute deviation (MAD) in robust statistics and adopt the X84 principle for adaptive outlier depression, ensuring a robust and stable registration. Subsequently, we propose a novel geometric invariant under rigid transformations to incorporate higher-order features of point clouds, which is further embedded for force modeling to guide the correspondence between pairwise scans credibly. Finally, we introduce an adaptive simulated annealing (ASA) method to search for the global optimum and substantially accelerate the registration process. We perform comprehensive experiments to evaluate the proposed method on various datasets captured from range scanners to LiDAR. Results demonstrate that our proposed method outperforms representative state-of-the-art approaches in terms of accuracy and is more suitable for registering large-scale point clouds. Furthermore, it is considerably faster and more robust than most competitors. Our implementation is publicly available at https://github.com/zikai1/GraphReg.

Fitting ellipses from unrecognized data is a fundamental problem in computer vision and pattern recognition. Classic least-squares based methods are sensitive to outliers. To address this problem, in this paper, we present a novel and effective method called hierarchical Gaussian mixture models (HGMM) for ellipse fitting in noisy, outliers-contained, and occluded settings on the basis of Gaussian mixture models (GMM). This method is crafted into two layers to significantly improve its fitting accuracy and robustness for data containing outliers/noise and has been proven to effectively narrow down the iterative interval of the kernel bandwidth, thereby speeding up ellipse fitting. Extensive experiments are conducted on synthetic data including substantial outliers (up to 60%) and strong noise (up to 200%) as well as on real images including complex benchmark images with heavy occlusion and images from versatile applications. We compare our results with those of representative state-of-the-art methods and demonstrate that our proposed method has several salient advantages, such as its high robustness against outliers and noise, high fitting accuracy, and improved performance.