Research map / Point clouds / Point cloud classification
Deep Parametric Continuous Convolutional Neural Networks
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 parametric continuous convolution layers instead of the SEGCloud approach | Point-cloud semantic labeling · Stanford Large-Scale 3D Indoor Scene Dataset | mIOU: 9.3% mIOU | Helped |
| Use parametric continuous convolution layers instead of the SEGCloud approach | Point-cloud semantic labeling · Stanford Large-Scale 3D Indoor Scene Dataset | mAcc: 9.6% mACC | Helped |
| Add seven residual continuous convolution layers to 3D-FCN | 3D-FCN for driving-scene point labeling · Driving Scenes Dataset | mIOU | Helped |
| Add seven residual continuous convolution layers to 3D-FCN | 3D-FCN for lidar motion estimation · Lidar Flow, Driving Scenes Dataset | EPE (cm): 0.351cm | Helped |
| Add seven residual continuous convolution layers to 3D-FCN | 3D-FCN for lidar motion estimation · Lidar Flow, Driving Scenes Dataset | Outlier percentage: approximately 20% | Helped |
Closest papers by meaning
- SMPConv: Self-Moving Point Representations for Continuous Convolution (CVPR 2023 · similarity 0.86)
- CKConv: Continuous Kernel Convolution For Sequential Data (ICLR 2022 · similarity 0.86)
- Continuous Parametric Optical Flow (NeurIPS 2023 · similarity 0.85)
- Learning Coordinate-based Convolutional Kernels for Continuous SE(3) Equivariant and Efficient Point Cloud Analysis (CVPR 2026 · similarity 0.85)
- Spherical CNNs on Unstructured Grids (ICLR 2019 · similarity 0.85)
- Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images (ICLR 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.