Research map / 3D vision / Face and shape
BSP-Net: Generating Compact Meshes via Binary Space Partitioning
Check 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 |
|---|---|---|---|
| Add overlap loss (ablation) | BSP-Net · ShapeNet (Part) auto-encoding | CD: 0.447 -> 0.448 | Hurt |
| Add overlap loss (ablation) | BSP-Net · ShapeNet (Part) auto-encoding | NC: 0.858 -> 0.858 | No clear effect |
| Add overlap loss (ablation) | BSP-Net · ShapeNet (Part) auto-encoding | LFD: 2019.26 -> 2030.35 | Hurt |
| Add overlap loss (ablation) | BSP-Net · ShapeNet (Part) segmentation | mean per-label IoU: 79.3 -> 79.8 | Helped |
| Fine-tune with discrete connections and the exact union after continuous relaxation (ablation) | BSP-Net · synthetic 2D auto-encoding | reconstruction quality | Helped |
Closest papers by meaning
- CvxNet: Learnable Convex Decomposition (CVPR 2020 · similarity 0.88)
- PolyGen: An Autoregressive Generative Model of 3D Meshes (ICML 2020 · similarity 0.88)
- MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers (CVPR 2024 · similarity 0.87)
- Neural Parts: Learning Expressive 3D Shape Abstractions With Invertible Neural Networks (CVPR 2021 · similarity 0.87)
- A Papier-Mâché Approach to Learning 3D Surface Generation (CVPR 2018 · similarity 0.87)
- NeuralSlice: Neural 3D Triangle Mesh Reconstruction via Slicing 4D Tetrahedral Meshes (ICML 2023 · similarity 0.87)
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.