CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction

• URL: http://arxiv.org/abs/2609.14521v1
• Date: Sun, 13 Sep 2026 13:56:44 GMT
• Title: CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction
• Abstract summary: We propose a Curve-Grounded Geometry Transformer that grounds 3D-consistent 2D curve instances in the image space from sparse, unposed multi-view images.<n>We show that our framework achieves substantial improvements in both reconstruction accuracy and efficiency.<n>Despite being trained solely on synthetic data, CGGT generalizes well to real-world images.
• Score: 31.822849244645525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recovering editable 3D parametric curves from 2D images is a fundamental challenge in computer graphics, bridging pixel-based perception and vector-based CAD modeling. Existing NeRF- and 3DGS-based methods often rely on dense calibrated views, precomputed 2D edge maps, and costly per-scene optimization, limiting their applicability to casually captured real-world inputs. We propose CGGT, a Curve-Grounded Geometry Transformer that directly grounds 3D-consistent 2D curve instances in the image space from sparse, unposed multi-view images. CGGT combines a geometry-aware transformer encoder for multi-view feature learning with a curve-aware masked-attention decoder for cross-view instance association. In a single forward pass, it predicts camera parameters, dense depth maps, and instance-level 2D curve masks, which are then lifted into 3D and refined through a fast parametric optimization stage to recover compact, editable 3D curve primitives. To support structured curve learning, we introduce Wireframe-100K, a large-scale dataset comprising 100,000 CAD models with diverse topologies, realistic multi-view renderings, and accurate parametric curve annotations. Extensive experiments show that our framework achieves substantial improvements in both reconstruction accuracy and efficiency, particularly under challenging sparse-view settings and in separating persistent 3D structural edges from view-dependent image edges caused by silhouettes, textures, and appearance variations. Despite being trained solely on synthetic data, CGGT generalizes well to real-world images, demonstrating its potential for practical CAD-style wireframe reconstruction from unconstrained visual inputs.

Related papers

• IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation [76.36174247570716]
  We propose IVGT, an Implicit Visual Geometry Transformer that implicitly models continuous and coherent geometry from pose-free multi-view images.<n> IVGT learns a continuous neural scene representation in a canonical coordinate system and supports continuous spatial queries at any 3D positions.<n>It allows direct extraction of continuous and coherent surface geometry, enabling rendering of RGB images, depth maps, and surface normal maps from arbitrary viewpoints.
  arXiv  Detail & Related papers  (2026-05-15T17:59:57Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• WIR3D: Visually-Informed and Geometry-Aware 3D Shape Abstraction [13.645442589551354]
  WIR3D is a technique for abstracting 3D shapes through a sparse set of visually meaningful curves in 3D.<n>We optimize the parameters of Bezier curves such that they faithfully represent both the geometry and salient visual features.<n>We successfully apply our method for shape abstraction over a broad dataset of shapes.
  arXiv  Detail & Related papers  (2025-05-07T21:28:05Z)
• SketchSplat: 3D Edge Reconstruction via Differentiable Multi-view Sketch Splatting [20.434979868697518]
  Edges are one of the most basic parametric primitives to describe structural information in 3D.<n>Previous methods usually reconstruct a 3D edge point set from multi-view 2D edge images, and then fit 3D edges to the point set.<n>We propose SketchSplat, a method to reconstruct accurate, complete, and compact 3D edges via differentiable multi-view sketch splatting.
  arXiv  Detail & Related papers  (2025-03-18T23:30:03Z)
• F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Aggregative Gaussian Splatting [35.625593119642424]
  This paper tackles the problem of generalizable 3D-aware generation from monocular datasets.<n>We propose a novel feed-forward pipeline based on pixel-aligned Gaussian Splatting.<n>We also introduce a self-supervised cycle-aggregative constraint to enforce cross-view consistency in the learned 3D representation.
  arXiv  Detail & Related papers  (2025-01-12T04:44:44Z)
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields [50.056790168812114]
  3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking.<n>We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images.<n>We demonstrate that our differentiable terms allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
  arXiv  Detail & Related papers  (2024-03-26T17:21:24Z)
• T-Pixel2Mesh: Combining Global and Local Transformer for 3D Mesh Generation from a Single Image [84.08705684778666]
  We propose a novel Transformer-boosted architecture, named T-Pixel2Mesh, inspired by the coarse-to-fine approach of P2M. Specifically, we use a global Transformer to control the holistic shape and a local Transformer to refine the local geometry details. Our experiments on ShapeNet demonstrate state-of-the-art performance, while results on real-world data show the generalization capability.
  arXiv  Detail & Related papers  (2024-03-20T15:14:22Z)
• Pixel2Mesh++: 3D Mesh Generation and Refinement from Multi-View Images [82.32776379815712]
  We study the problem of shape generation in 3D mesh representation from a small number of color images with or without camera poses. We adopt to further improve the shape quality by leveraging cross-view information with a graph convolution network. Our model is robust to the quality of the initial mesh and the error of camera pose, and can be combined with a differentiable function for test-time optimization.
  arXiv  Detail & Related papers  (2022-04-21T03:42:31Z)
• Beyond 3DMM: Learning to Capture High-fidelity 3D Face Shape [77.95154911528365]
  3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. Previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry. This paper proposes a complete solution to capture the personalized shape so that the reconstructed shape looks identical to the corresponding person.
  arXiv  Detail & Related papers  (2022-04-09T03:46:18Z)
• To The Point: Correspondence-driven monocular 3D category reconstruction [39.811816510186475]
  To The Point (TTP) is a method for reconstructing 3D objects from a single image using 2D to 3D correspondences learned from weak supervision. We replace CNN-based regression of camera pose and non-rigid deformation and obtain substantially more accurate 3D reconstructions.
  arXiv  Detail & Related papers  (2021-06-10T11:21:14Z)

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.