FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models

• URL: http://arxiv.org/abs/2506.16627v1
• Date: Thu, 19 Jun 2025 21:54:08 GMT
• Title: FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models
• Abstract summary: We present a curvature proxy that regularizes only the mixed second-order term.<n>Because the method is drop-in and framework-agnostic, it opens a practical path toward scalable, curvature-aware SDF learning.
• Score: 41.13351630648502
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural signed-distance fields (SDFs) have become a versatile backbone for geometric learning, yet enforcing developable, CAD-style behavior still hinges on Gaussian curvature penalties that require full Hessian evaluation and second-order automatic differentiation, both of which are costly in memory and runtime. We present a curvature proxy that regularizes only the mixed second-order term (Weingarten term), allowing the two principal curvatures to adapt freely to data while suppressing unwanted warp. Two complementary instantiations realize this idea: (i) a finite-difference proxy that replaces each Hessian entry with four forward SDF evaluations and a single first-order gradient, and (ii) an autodiff proxy that computes the same mixed derivative via one Hessian-vector product, sidestepping explicit full Hessian assembly and remaining faster in practice. Both variants converge to the exact mixed second derivative, thus preserving the intended geometric bias without incurring full second-order graphs. On the ABC benchmarks, the proxies match or exceed the reconstruction fidelity of Hessian-based baselines while reducing GPU memory use and wall-clock time by a factor of two. Because the method is drop-in and framework-agnostic, it opens a practical path toward scalable, curvature-aware SDF learning for engineering-grade shape reconstruction.

Related papers

• CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation [41.42805325196858]
  We introduce CubicSplat, a new type of vector graphics solver that replaces Bézier closest-point solvers with uniform polyline surrogates whose geometric error is bounded at $O(S-2)$.<n>The resulting static computation graph yields well-conditioned gradients by construction, while a PSN-derived visibility mechanism prunes primitives without auxiliary regularization.
  arXiv  Detail & Related papers  (2026-08-21T07:21:08Z)
• Shape: A Self-Supervised 3D Geometry Foundation Model for Industrial CAD Analysis [0.19116784879310025]
  Industrial CAD require robust, generalizable 3D representations supporting accuracy and explainability.<n>We introduce Shape, a self-supervised foundation model converting surface meshes into dense per-token embeddings.
  arXiv  Detail & Related papers  (2026-04-19T11:59:36Z)
• A Finite Difference Approximation of Second Order Regularization of Neural-SDFs [39.799207552858114]
  We introduce a finite-difference framework for curvature regularization in neural signed distance field (SDF) learning.<n> Experiments demonstrate that our finite-difference variants achieve reconstruction fidelity comparable to their automatic-differentiation counterparts.
  arXiv  Detail & Related papers  (2025-11-12T04:56:08Z)
• Gaussian Splatting with Discretized SDF for Relightable Assets [20.523085632567717]
  3D Gaussian splatting (3DGS) has shown its detailed expressive ability and highly efficient rendering speed in the novel view synthesis (NVS) task.<n>The application to inverse rendering still faces several challenges, as the discrete nature of Gaussian primitives makes it difficult to apply geometry constraints.<n>Recent works introduce the signed distance field (SDF) as an extra continuous representation to regularize the geometry defined by Gaussian primitives.<n>We introduce a discretized SDF to represent the continuous SDF in a discrete manner by encoding it within each Gaussian using a sampled value.
  arXiv  Detail & Related papers  (2025-07-21T13:52:33Z)
• Curve-Aware Gaussian Splatting for 3D Parametric Curve Reconstruction [14.628742412460346]
  This paper presents an end-to-end framework for reconstructing 3D parametric curves directly from multi-view edge maps.<n>We propose a novel bi-directional coupling mechanism between parametric curves and edge-oriented Gaussian components.<n>Our method significantly reduces the parameter count during training, achieving both higher efficiency and superior performance compared to existing approaches.
  arXiv  Detail & Related papers  (2025-06-26T15:48:08Z)
• FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models [49.397861654088636]
  We propose a two-step procedure to approximate SVD/QR-based gradient projections into lower-dimensional spaces.<n>We show that our strategy achieves faster runtime and reduced memory usage by up to $25%$ across different model sizes.
  arXiv  Detail & Related papers  (2025-05-23T14:37:00Z)
• Enabling Automatic Differentiation with Mollified Graph Neural Operators [75.3183193262225]
  We propose the mollified graph neural operator (mGNO), the first method to leverage automatic differentiation and compute emphexact gradients on arbitrary geometries.<n>For a PDE example on regular grids, mGNO paired with autograd reduced the L2 relative data error by 20x compared to finite differences.<n>It can also solve PDEs on unstructured point clouds seamlessly, using physics losses only, at resolutions vastly lower than those needed for finite differences to be accurate enough.
  arXiv  Detail & Related papers  (2025-04-11T06:16:30Z)
• Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds [69.69726932986923]
  We propose the scaled-squared distance function (S$2$DF), a novel implicit surface representation for modeling arbitrary surface types.<n>S$2$DF does not distinguish between inside and outside regions while effectively addressing the non-differentiability issue of UDF at the zero level set.
  arXiv  Detail & Related papers  (2024-10-24T06:56:34Z)
• GeoCalib: Learning Single-image Calibration with Geometric Optimization [89.84142934465685]
  From a single image, visual cues can help deduce intrinsic and extrinsic camera parameters like the focal length and the gravity direction. Current approaches to this problem are based on either classical geometry with lines and vanishing points or on deep neural networks trained end-to-end. We introduce GeoCalib, a deep neural network that leverages universal rules of 3D geometry through an optimization process.
  arXiv  Detail & Related papers  (2024-09-10T17:59:55Z)
• Split-and-Fit: Learning B-Reps via Structure-Aware Voronoi Partitioning [50.684254969269546]
  We introduce a novel method for acquiring boundary representations (B-Reps) of 3D CAD models. We apply a spatial partitioning to derive a single primitive within each partition. We show that our network, coined NVD-Net for neural Voronoi diagrams, can effectively learn Voronoi partitions for CAD models from training data.
  arXiv  Detail & Related papers  (2024-06-07T21:07:49Z)
• Global $\mathcal{L}^2$ minimization at uniform exponential rate via geometrically adapted gradient descent in Deep Learning [1.4050802766699084]
  We consider the scenario of supervised learning in Deep Learning (DL) networks.<n>We choose the gradient flow with respect to the Euclidean metric in the output layer of the DL network.
  arXiv  Detail & Related papers  (2023-11-27T02:12:02Z)
• Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths [54.53208538517505]
  This paper addresses learning end-to-end models for time series data that include a temporal alignment step via dynamic time warping (DTW) We propose a DTW layer based around bi-level optimisation and deep declarative networks, which we name DecDTW. We show that this property is particularly useful for applications where downstream loss functions are defined on the optimal alignment path itself.
  arXiv  Detail & Related papers  (2023-03-19T21:58:37Z)
• Reconstructing editable prismatic CAD from rounded voxel models [16.03976415868563]
  We introduce a novel neural network architecture to solve this challenging task. Our method reconstructs the input geometry in the voxel space by decomposing the shape. During inference, we obtain the CAD data by first searching a database of 2D constrained sketches.
  arXiv  Detail & Related papers  (2022-09-02T16:44:10Z)
• Error-Correcting Neural Networks for Two-Dimensional Curvature Computation in the Level-Set Method [0.0]
  We present an error-neural-modeling-based strategy for approximating two-dimensional curvature in the level-set method. Our main contribution is a redesigned hybrid solver that relies on numerical schemes to enable machine-learning operations on demand.
  arXiv  Detail & Related papers  (2022-01-22T05:14:40Z)
• Point2Cyl: Reverse Engineering 3D Objects from Point Clouds to Extrusion Cylinders [25.389088434370066]
  We propose Point2Cyl, a supervised network transforming a raw 3D point cloud to a set of extrusion cylinders. Our approach demonstrates the best performance on two recent CAD datasets.
  arXiv  Detail & Related papers  (2021-12-17T05:22:28Z)
• Implicit SVD for Graph Representation Learning [33.761179632722]
  We make Graph Representational Learning more computationally tractable for those with modest hardware. We derive linear approximation of a SOTA model, and train the model, in closed-form, via SVD of $mathbfM$, without calculating entries. Our models show competitive empirical test performance over various graphs.
  arXiv  Detail & Related papers  (2021-11-11T16:58:17Z)
• Unfolding Projection-free SDP Relaxation of Binary Graph Classifier via GDPA Linearization [59.87663954467815]
  Algorithm unfolding creates an interpretable and parsimonious neural network architecture by implementing each iteration of a model-based algorithm as a neural layer. In this paper, leveraging a recent linear algebraic theorem called Gershgorin disc perfect alignment (GDPA), we unroll a projection-free algorithm for semi-definite programming relaxation (SDR) of a binary graph. Experimental results show that our unrolled network outperformed pure model-based graph classifiers, and achieved comparable performance to pure data-driven networks but using far fewer parameters.
  arXiv  Detail & Related papers  (2021-09-10T07:01:15Z)
• Cogradient Descent for Dependable Learning [64.02052988844301]
  We propose a dependable learning based on Cogradient Descent (CoGD) algorithm to address the bilinear optimization problem. CoGD is introduced to solve bilinear problems when one variable is with sparsity constraint. It can also be used to decompose the association of features and weights, which further generalizes our method to better train convolutional neural networks (CNNs)
  arXiv  Detail & Related papers  (2021-06-20T04:28:20Z)
• Learning Deformable Tetrahedral Meshes for 3D Reconstruction [78.0514377738632]
  3D shape representations that accommodate learning-based 3D reconstruction are an open problem in machine learning and computer graphics. Previous work on neural 3D reconstruction demonstrated benefits, but also limitations, of point cloud, voxel, surface mesh, and implicit function representations. We introduce Deformable Tetrahedral Meshes (DefTet) as a particular parameterization that utilizes volumetric tetrahedral meshes for the reconstruction problem.
  arXiv  Detail & Related papers  (2020-11-03T02:57:01Z)
• Cogradient Descent for Bilinear Optimization [124.45816011848096]
  We introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent. Our algorithm is applied to solve problems with one variable under the sparsity constraint.
  arXiv  Detail & Related papers  (2020-06-16T13:41:54Z)
• Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks [1.3706331473063877]
  We show that the solution of training a width-$n$ shallow ReLU network is within $n- 1/2$ of the function which fits the training data. We also show that the training trajectories are captured by trajectories of smoothing splines with decreasing regularization strength.
  arXiv  Detail & Related papers  (2020-06-12T17:46:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.