Research map / Point clouds / Segmentation and detection
SpSequenceNet: Semantic Segmentation Network on 4D Point Clouds
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 cross-frame global attention (ablation) | SpSequenceNet backbone · SemanticKITTI | mIoU: 41.9 -> 42.6 | Helped |
| Add top-3 cross-frame local interpolation (ablation) | Backbone+CGA · SemanticKITTI | mIoU: 42.6 -> 43.1 | Helped |
| Use top-1 instead of top-3 neighbors for cross-frame local interpolation (ablation) | Backbone+CGA+CLI · SemanticKITTI | mIoU: 42.6 -> 42.0 | Hurt |
| Add cross-frame global attention and cross-frame local interpolation | SemanticKITTI segmentation · SemanticKITTI test | mIoU: +1.5% | Helped |
| Use separate prediction heads for single-frame semantics and motion status (ablation) | Backbone+CGA+CLI-3 · SemanticKITTI single-frame task | mIoU: +1.6% | Helped |
| Use separate prediction heads rather than reorganized outputs (ablation) | Backbone+CGA+CLI-3 · SemanticKITTI motion status segmentation | mIoU: 37.9 -> 39.9 | Helped |
| Use separate prediction heads rather than reorganized outputs (ablation) | Backbone+CGA+CLI-3 · SemanticKITTI single-frame task | mIoU: 57.l -> 56.0 | Hurt |
Closest papers by meaning
- PointGS: Semantic-Consistent Unsupervised 3D Point Cloud Segmentation with 3D Gaussian Splatting (CVPR 2026 · similarity 0.89)
- 3D Semantic Segmentation With Submanifold Sparse Convolutional Networks (CVPR 2018 · similarity 0.89)
- PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017 · similarity 0.88)
- X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer (AAAI 2024 · similarity 0.88)
- Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-Based Sequence to Sequence Network (AAAI 2019 · similarity 0.88)
- DyPolySeg: Taylor Series-Inspired Dynamic Polynomial Fitting Network for Few-shot Point Cloud Semantic Segmentation (ICML 2025 · 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.