mlsanityData to 14 Oct 2026

Curvy: A Parametric Cross-section based Surface Reconstruction

arXiv 2409.00829 ↗First posted 1 Sep 2024cs.CV cs.CG cs.GRcited by 0

Not on the map. Why?

Abstract (arXiv)

In this work, we present a novel approach for reconstructing shape point clouds using planar sparse cross-sections with the help of generative modeling. We present unique challenges pertaining to the representation and reconstruction in this problem setting. Most methods in the classical literature lack the ability to generalize based on object class and employ complex mathematical machinery to reconstruct reliable surfaces. We present a simple learnable approach to generate a large number of points from a small number of input cross-sections over a large dataset. We use a compact parametric polyline representation using adaptive splitting to represent the cross-sections and perform learning using a Graph Neural Network to reconstruct the underlying shape in an adaptive manner reducing the dependence on the number of cross-sections provided.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 1 Sep 2024.

Builds on

17 of 37 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  7. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  9. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  10. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  11. 2021Shape As Points: A Differentiable Poisson Solvercited by 187
  12. 2017Learning Efficient Point Cloud Generation for Dense 3D Object Reconstructioncited by 133
5 more
  1. 2020Towards Deeper Graph Neural Networks with Differentiable Group Normalizationcited by 114
  2. 2020Point Cloud Completion by Skip-attention Network with Hierarchical Foldingcited by 106
  3. 2019Multi-Angle Point Cloud-VAE: Unsupervised Feature Learning for 3D Point Clouds from Multiple Angles by Joint Self-Reconstruction and Half-to-Half Predictioncited by 66
  4. 2019RL-GAN-Net: A Reinforcement Learning Agent Controlled GAN Network for Real-Time Point Cloud Shape Completioncited by 58
  5. 2018Topology-Aware Surface Reconstruction for Point Cloudscited by 21

Built on by

Not cited yet.