Learning Convex Decomposition via Feature Fields

• URL: http://arxiv.org/abs/2603.09285v1
• Date: Tue, 10 Mar 2026 07:07:55 GMT
• Title: Learning Convex Decomposition via Feature Fields
• Abstract summary: This work proposes a new formulation to the long-standing problem of convex decomposition through learning feature fields.<n>Our method produces decompositions of 3D shapes of convex bodies.<n>Our formulation can be used for single shape optimization, but more importantly, prediction unlocks scalable, self-supervised learning.
• Score: 39.95179829013123
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This work proposes a new formulation to the long-standing problem of convex decomposition through learning feature fields, enabling the first feed-forward model for open-world convex decomposition. Our method produces high-quality decompositions of 3D shapes into a union of convex bodies, which are essential to accelerate collision detection in physical simulation, amongst many other applications. The key insight is to adopt a feature learning approach and learn a continuous feature field that can later be clustered to yield a good convex decomposition via our self-supervised, purely-geometric objective derived from the classical definition of convexity. Our formulation can be used for single shape optimization, but more importantly, feature prediction unlocks scalable, self-supervised learning on large datasets resulting in the first learned open-world model for convex decomposition. Experiments show that our decompositions are higher-quality than alternatives and generalize across open-world objects as well as across representations to meshes, CAD models, and even Gaussian splats. https://research.nvidia.com/labs/sil/projects/learning-convex-decomp/

Related papers

• D-Convexity: A Unified Differentiable Convex Shape Prior via Quasi-Concavity for Data-driven Image Segmentation [5.445483153964301]
  Convexity is a fundamental geometric prior that underlies many natural and man-made structures.<n>We propose a unified, threshold-free convexity prior based on the quasi-concavity of the network's output mask function u.<n>Our analysis unifies a wide spectrum of previous convex shape models, from discrete 1-0-1 line constraints to curvature or signed distance Laplacian based level-set priors.
  arXiv  Detail & Related papers  (2026-05-19T00:27:41Z)
• SpaceMesh: A Continuous Representation for Learning Manifold Surface Meshes [61.110517195874074]
  We present a scheme to directly generate manifold, polygonal meshes of complex connectivity as the output of a neural network.<n>Our key innovation is to define a continuous latent connectivity space at each mesh, which implies the discrete mesh.<n>In applications, this approach not only yields high-quality outputs from generative models, but also enables directly learning challenging geometry processing tasks such as mesh repair.
  arXiv  Detail & Related papers  (2024-09-30T17:59:03Z)
• The Convex Landscape of Neural Networks: Characterizing Global Optima and Stationary Points via Lasso Models [75.33431791218302]
  Deep Neural Network Network (DNN) models are used for programming purposes. In this paper we examine the use of convex neural recovery models. We show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program. We also show that all the stationary non-dimensional objective objective can be characterized as the standard a global subsampled convex solvers program.
  arXiv  Detail & Related papers  (2023-12-19T23:04:56Z)
• Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search [23.52274863244624]
  Approximate convex decomposition aims to decompose a 3D shape into a set of almost convex components. It has been widely used in game engines, physics simulations, and animation. We propose a novel method that addresses the limitations of existing approaches from three perspectives.
  arXiv  Detail & Related papers  (2022-05-05T23:40:15Z)
• Neural Fields as Learnable Kernels for 3D Reconstruction [101.54431372685018]
  We present a novel method for reconstructing implicit 3D shapes based on a learned kernel ridge regression. Our technique achieves state-of-the-art results when reconstructing 3D objects and large scenes from sparse oriented points.
  arXiv  Detail & Related papers  (2021-11-26T18:59:04Z)
• Regularization of Mixture Models for Robust Principal Graph Learning [0.0]
  A regularized version of Mixture Models is proposed to learn a principal graph from a distribution of $D$-dimensional data points. Parameters of the model are iteratively estimated through an Expectation-Maximization procedure.
  arXiv  Detail & Related papers  (2021-06-16T18:00:02Z)
• Optimal Pose and Shape Estimation for Category-level 3D Object Perception [24.232254155643574]
  category-level perception problem, where one is given 3D sensor data picturing an object of a given category. We provide the first certifiably optimal CAD solver for pose and shape estimation. We also develop the first graph-theoretic formulation to prune outliers in category-level perception.
  arXiv  Detail & Related papers  (2021-04-16T21:41:29Z)
• Dense Non-Rigid Structure from Motion: A Manifold Viewpoint [162.88686222340962]
  Non-Rigid Structure-from-Motion (NRSfM) problem aims to recover 3D geometry of a deforming object from its 2D feature correspondences across multiple frames. We show that our approach significantly improves accuracy, scalability, and robustness against noise.
  arXiv  Detail & Related papers  (2020-06-15T09:15:54Z)
• Convex Shape Prior for Deep Neural Convolution Network based Eye Fundus Images Segmentation [6.163107242394357]
  We propose a technique which can be easily integrated into the commonly used DCNNs for image segmentation. Our method is based on the dual representation of the sigmoid activation function in DCNNs. We show that our method is efficient and outperforms the classical DCNN segmentation methods.
  arXiv  Detail & Related papers  (2020-05-15T11:36:04Z)
• Learning Bijective Feature Maps for Linear ICA [73.85904548374575]
  We show that existing probabilistic deep generative models (DGMs) which are tailor-made for image data, underperform on non-linear ICA tasks. To address this, we propose a DGM which combines bijective feature maps with a linear ICA model to learn interpretable latent structures for high-dimensional data. We create models that converge quickly, are easy to train, and achieve better unsupervised latent factor discovery than flow-based models, linear ICA, and Variational Autoencoders on images.
  arXiv  Detail & Related papers  (2020-02-18T17:58:07Z)

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.