CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation

• URL: http://arxiv.org/abs/2608.20803v1
• Date: Fri, 21 Aug 2026 07:21:08 GMT
• Title: CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation
• Abstract summary: 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.
• Score: 41.42805325196858
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vector graphics are prized for their resolution independence, compact storage, and direct editability, making differentiable optimization of their parametric primitives an attractive goal. Yet classical rasterization is discontinuous with respect to geometry, and existing remedies that smooth the forward pass demand increasingly elaborate heuristics as scene complexity grows. We trace this fragility to a gradient seesaw: design choices that improve forward geometric exactness can systematically degrade the induced gradient signal, and vice versa. To navigate this tension we introduce CubicSplat, a differentiable vector rasterizer that replaces Bézier closest-point solvers with uniform polyline surrogates whose geometric error is bounded at $O(S^{-2})$. The resulting static computation graph yields well-conditioned gradients by construction, while a compositing-derived visibility mechanism prunes degenerate primitives without auxiliary regularization. On DIV2K and Kodak benchmarks CubicSplat achieves state-of-the-art reconstruction quality with over 2 dB PSNR gain in the closed-fill setting, while training up to 4x faster than prior methods. The code is available at https://github.com/CubicSplat/repo

Related papers

• Stable and Scalable Bundle Adjustment of Holistic 3D Structures [99.03818732955783]
  We present a new version of Bundle Adjustment (BA) for 3D computer vision.<n>BA is developed to jointly optimize cameras, poses and 3D points.<n>By group-induced measurements and cross-feature reprojection, we preserve the sparsity of classical point-only 3D regularization.
  arXiv  Detail & Related papers  (2026-09-03T16:08:03Z)
• Vector Scaffolding: Inter-Scale Orchestration for Differentiable Image Vectorization [48.98909774916165]
  We propose a novel hierarchical optimization framework that shifts from flat pixel-matching to structured topological construction tailored for vector graphics.<n> Experiments demonstrate that our approach accelerates optimization by $2.5times$ while simultaneously improving PSNR by up to 1.4 dB over the previous state of the art.
  arXiv  Detail & Related papers  (2026-05-12T10:27:30Z)
• GSMap: 2D Gaussians for Online HD Mapping [8.653416286011359]
  We propose GSMap, a novel framework that unifies both paradigms via a learnable 2D representation.<n>Experiments on both nuScenes and Argoverse2 demonstrate that our Gaussian-based representation effectively unifies geometric and topological learning.
  arXiv  Detail & Related papers  (2026-05-10T15:57:07Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• 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)
• FlatCAD: Fast Curvature Regularization of Neural SDFs for CAD Models [37.56003520528009]
  We introduce an off-diagonal Weingarten loss that regularizes only the mixed shape operator term.<n>We present two variants: a finite-difference version using six SDF evaluations plus one gradient, and an auto-diff version using a single Hessian-vector product.<n>The method is drop-in and framework-agnostic, enabling scalable curvature-aware SDF learning for engineering-grade shape reconstruction.
  arXiv  Detail & Related papers  (2025-06-19T21:54:08Z)
• StableGS: A Floater-Free Framework for 3D Gaussian Splatting [9.935869165752283]
  3D Gaussian Splatting (3DGS) reconstructions are plagued by stubborn floater" artifacts that degrade their geometric and visual fidelity.<n>We propose StableGS, a novel framework that decouples geometric regularization from final appearance rendering.<n> Experiments on multiple benchmarks show StableGS not only eliminates floaters but also resolves the common blur-artifact trade-off.
  arXiv  Detail & Related papers  (2025-03-24T09:02:51Z)
• BG-Triangle: Bézier Gaussian Triangle for 3D Vectorization and Rendering [60.240908644910874]
  Differentiable rendering enables efficient optimization by allowing gradients to be computed through the rendering process.<n>Existing solutions approximate or re-formulate traditional rendering operations using smooth, probabilistic proxies.<n>We present a novel hybrid representation that combines B'ezier triangle-based vector graphics primitives with Gaussian-based probabilistic models.
  arXiv  Detail & Related papers  (2025-03-18T06:53:52Z)
• 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)

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.