Research map / Point clouds / Point cloud classification
DRINet: A Dual-Representation Iterative Learning Network for Point Cloud Segmentation
Maosheng Ye, Shuangjie Xu, Tongyi Cao, Qifeng Chen
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 SVPFE (voxel branch) to a point-only network (ablation) | DRINet · SemanticKITTI val | mIoU: 48.6 -> 67.3 | Improved |
| add SPVFE (point branch) to a voxel-only network (ablation) | DRINet · SemanticKITTI val | mIoU: 63.4 -> 67.3 | Improved |
| add multi-scale pooling layer (ablation) | DRINet · SemanticKITTI val | mIoU: 65.4 -> 67.3 | Improved |
| add attentive gathering instead of nearest gathering (ablation) | DRINet · SemanticKITTI val | mIoU: 64.6 -> 65.4 | Improved |
| increase SPVFE and SVPFE blocks from 3 to 4 (ablation) | DRINet · SemanticKITTI val | mIoU: 67.3 -> 67.6, inference 62ms -> 72ms | Mixed |
| increase block number from 1 to 4 (ablation) | DRINet · SemanticKITTI val | mIoU: 58.2% to 67.6% | Improved |
| increase block number from 1 to 4 (ablation) | DRINet · S3DIS | mIoU: 36.3% to 66.7% | Improved |
| use GAFE geometry-aware features instead of PointNet++ features (ablation) | feature extractor · SemanticKITTI val | mIoU: 18.1 -> 22.8 | Improved |
| use DRINet instead of SPVNet | SemanticKITTI segmentation · SemanticKITTI test | mIoU / speed (ms): 67.0 -> 67.5 mIoU, 259 -> 62 ms | Improved |
| use DRINet instead of PVCNN | ShapeNet Parts segmentation · ShapeNet Parts | mIoU / latency (ms): 86.2 -> 86.4 mIoU, 50.7 -> 30 ms | Improved |
| use DRINet instead of KPConv | S3DIS Area 5 · S3DIS Area 5 | mIoU: 67.1 -> 66.7 | Hurt |
Later papers that compared with this method
1 later accepted paper reports DRINet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks (ECCV 2022 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.
- PolarNet — PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation (CVPR 2020) · better on 1 of 2 shared results
- PointCNN — PointCNN: Convolution On X-Transformed Points (NeurIPS 2018) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Efficient Point Cloud Segmentation with Geometry-Aware Sparse Networks (ECCV 2022 · similarity 0.87)
- ASSANet: An Anisotropic Separable Set Abstraction for Efficient Point Cloud Representation Learning (NeurIPS 2021 · similarity 0.87)
- DeepLA-Net: Very Deep Local Aggregation Networks for Point Cloud Analysis (CVPR 2025 · similarity 0.86)
- Point Cloud Pre-training with Diffusion Models (CVPR 2024 · similarity 0.86)
- LinNet: Linear Network for Efficient Point Cloud Representation Learning (NeurIPS 2024 · similarity 0.85)
- A Linear Time and Space Local Point Cloud Geometry Encoder via Vectorized Kernel Mixture (VecKM) (ICML 2024 · similarity 0.85)
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.
