Research map / Point clouds / Point cloud classification
SchellingFormer: Laplacian Matrix-guided Geometric Transformer for Robust Schelling Point Detection
Yihao Chen, Haobo Jiang, Liang Yu, Jianmin Zheng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 Gaussian curvature to coordinates (ablation) | SchellingFormer · Schelling point dataset (340 train / 60 test) | F1: 0.54705 -> 0.63927 | Improved |
| add Gaussian curvature difference (ablation) | SchellingFormer · Schelling point dataset (340 train / 60 test) | F1: 0.63927 -> 0.64224 | No clear effect |
| add Gaussian curvature difference (ablation) | SchellingFormer · Schelling point dataset (340 train / 60 test) | MDE: 0.01584 -> 0.01689 | Hurt |
| add Laplacian-guided vector attention (ablation) | SchellingFormer · Schelling point dataset (340 train / 60 test) | F1: 0.6422 -> 0.6507 | Improved |
| add Laplacian-guided vector attention (ablation) | SchellingFormer · Schelling point dataset (340 train / 60 test) | MDE: 0.01689 -> 0.01598 | Improved |
| add Laplacian-guided vector attention (ablation) | SchellingFormer · Schelling point dataset (340 train / 60 test) | FDR: 0.24803 -> 0.24827 | No clear effect |
| replace CNN backbone with Transformer (ablation) | SchellingFormer · Schelling point dataset (340 train / 60 test) | F1: 0.4872 -> 0.6507 | Improved |
| integrate baseline into SPHM regression framework | PointNet++ · Schelling point dataset (340 train / 60 test) | F1: 0.4103 -> 0.4498 | Improved |
| integrate baseline into SPHM regression framework | DynGraphCNN · Schelling point dataset (340 train / 60 test) | F1: 0.4347 -> 0.4699 | Improved |
Closest papers by meaning
- Laplacian Mesh Transformer: Dual Attention and Topology Aware Network for 3D Mesh Classification and Segmentation (ECCV 2022 · similarity 0.88)
- PointCFormer: A Relation-Based Progressive Feature Extraction Network for Point Cloud Completion (AAAI 2025 · similarity 0.85)
- GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer (ICCV 2025 · similarity 0.85)
- GPSFormer: A Global Perception and Local Structure Fitting-based Transformer for Point Cloud Understanding (ECCV 2024 · similarity 0.85)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.84)
- ShapeFormer: Transformer-Based Shape Completion via Sparse Representation (CVPR 2022 · 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.
