UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree

• URL: http://arxiv.org/abs/2006.09102v3
• Date: Tue, 20 Oct 2020 17:32:15 GMT
• Title: UCSG-Net -- Unsupervised Discovering of Constructive Solid Geometry Tree
• Authors: Kacper Kania, Maciej Zi\k{e}ba, Tomasz Kajdanowicz
• Abstract summary: Existing approaches to 3D shape reconstruction are supervised and require the entire CSG primitive tree that is given upfront during the process. We show that our model predicts parameters of an operation and parses their representation through differentiable indicator function. We show that our model is interpretable and can be used in software.
• Score: 6.605824452872053
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Signed distance field (SDF) is a prominent implicit representation of 3D meshes. Methods that are based on such representation achieved state-of-the-art 3D shape reconstruction quality. However, these methods struggle to reconstruct non-convex shapes. One remedy is to incorporate a constructive solid geometry framework (CSG) that represents a shape as a decomposition into primitives. It allows to embody a 3D shape of high complexity and non-convexity with a simple tree representation of Boolean operations. Nevertheless, existing approaches are supervised and require the entire CSG parse tree that is given upfront during the training process. On the contrary, we propose a model that extracts a CSG parse tree without any supervision - UCSG-Net. Our model predicts parameters of primitives and binarizes their SDF representation through differentiable indicator function. It is achieved jointly with discovering the structure of a Boolean operators tree. The model selects dynamically which operator combination over primitives leads to the reconstruction of high fidelity. We evaluate our method on 2D and 3D autoencoding tasks. We show that the predicted parse tree representation is interpretable and can be used in CAD software.

Related papers

• PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction [27.98261111833689]
  We propose PyTorchGeoNodes, a differentiable module for reconstructing 3D objects from images using interpretable shape programs. In our experiments, we apply our algorithm to reconstruct 3D objects in the ScanNet dataset and evaluate our results against CAD model retrieval-based reconstructions.
  arXiv  Detail & Related papers  (2024-04-16T14:43:33Z)
• 3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow [61.62796058294777]
  Reconstructing 3D shape from a single 2D image is a challenging task. Most of the previous methods still struggle to extract semantic attributes for 3D reconstruction task. We propose 3DAttriFlow to disentangle and extract semantic attributes through different semantic levels in the input images.
  arXiv  Detail & Related papers  (2022-03-29T02:03:31Z)
• RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures [18.5420635041504]
  RIM-Net is a neural network which learns implicit fields for unsupervised inference of hierarchical shape structures. We show the quality, consistency, and interpretability of hierarchical structural inference by RIM-Net.
  arXiv  Detail & Related papers  (2022-01-30T09:31:24Z)
• Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks [118.20778308823779]
  We present a novel 3D primitive representation that defines primitives using an Invertible Neural Network (INN) Our model learns to parse 3D objects into semantically consistent part arrangements without any part-level supervision.
  arXiv  Detail & Related papers  (2021-03-18T17:59:31Z)
• Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes [77.6741486264257]
  We introduce an efficient neural representation that, for the first time, enables real-time rendering of high-fidelity neural SDFs. We show that our representation is 2-3 orders of magnitude more efficient in terms of rendering speed compared to previous works.
  arXiv  Detail & Related papers  (2021-01-26T18:50:22Z)
• Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image [102.44347847154867]
  We propose a novel formulation that allows to jointly recover the geometry of a 3D object as a set of primitives. Our model recovers the higher level structural decomposition of various objects in the form of a binary tree of primitives. Our experiments on the ShapeNet and D-FAUST datasets demonstrate that considering the organization of parts indeed facilitates reasoning about 3D geometry.
  arXiv  Detail & Related papers  (2020-04-02T17:58:05Z)
• PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions [66.87405921626004]
  This paper investigates the novel problem of generating 3D shape point cloud geometry from a symbolic part tree representation. We propose a conditional GAN "part tree"-to-"point cloud" model (PT2PC) that disentangles the structural and geometric factors.
  arXiv  Detail & Related papers  (2020-03-19T08:27:25Z)
• Unsupervised Learning of Intrinsic Structural Representation Points [50.92621061405056]
  Learning structures of 3D shapes is a fundamental problem in the field of computer graphics and geometry processing. We present a simple yet interpretable unsupervised method for learning a new structural representation in the form of 3D structure points.
  arXiv  Detail & Related papers  (2020-03-03T17:40:00Z)

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.