Research map / 3D vision / Face and shape
UCSG-NET- Unsupervised Discovering of Constructive Solid Geometry Tree
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use unsupervised CSG-tree discovery instead of supervised or RL CSG-NetStack | 2D CAD reconstruction · CAD dataset validation | Chamfer Distance: 0.34 -> 0.32 | Helped |
| Use UCSG-Net instead of BSP-Net | 3D reconstruction · ShapeNet 3D autoencoding | Chamfer Distance: 0.446 -> 2.085 | Hurt |
| Add dropout or L2 regularization to the operand-selection matrices (ablation) | UCSG-Net · CAD dataset | Chamfer Distance | Hurt |
| Condition operand-selection matrices on the layer-specific latent code (ablation) | UCSG-Net · CAD dataset | Chamfer Distance | Hurt |
Closest papers by meaning
- D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts (NeurIPS 2023 · similarity 0.90)
- BSP-Net: Generating Compact Meshes via Binary Space Partitioning (CVPR 2020 · similarity 0.86)
- PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction (CVPR 2025 · similarity 0.85)
- MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction (NeurIPS 2025 · similarity 0.84)
- Unsigned Orthogonal Distance Fields: An Accurate Neural Implicit Representation for Diverse 3D Shapes (CVPR 2024 · similarity 0.84)
- Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.