Research map / Point clouds / Point cloud classification
PointINet: Point Cloud Frame Interpolation Network
Fan Lu, Guang Chen, Sanqing Qu, Zhijun Li, Yinlong Liu, Alois Knoll
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 |
|---|---|---|---|
| use PointINet instead of Scene flow | Point Cloud Frame Interpolation · KITTI odometry | CD: 0.687 -> 0.457 | Improved |
| use PointINet instead of Scene flow | Point Cloud Frame Interpolation · KITTI odometry | EMD: 57.13 -> 39.46 | Improved |
| use PointINet instead of Scene flow | Point Cloud Frame Interpolation · nuScenes | CD: 0.511 -> 0.487 | Improved |
| use PointINet instead of Scene flow | Point Cloud Frame Interpolation · nuScenes | EMD: 50.97 -> 47.98 | Improved |
| add adaptive sampling based on target time step (ablation) | PointINet · KITTI odometry | CD: 0.580 -> 0.457 | Improved |
| add adaptive sampling based on target time step (ablation) | PointINet · KITTI odometry | EMD: 48.00 -> 39.46 | Improved |
| add time-step-adaptive neighbor allocation in kNN clusters (ablation) | PointINet · KITTI odometry | CD: 0.534 -> 0.457 | Improved |
| add time-step-adaptive neighbor allocation in kNN clusters (ablation) | PointINet · KITTI odometry | EMD: 41.66 -> 39.46 | Improved |
| add attentive points fusion (ablation) | PointINet · KITTI odometry | CD: 0.555 -> 0.457 | Improved |
| add attentive points fusion (ablation) | PointINet · KITTI odometry | EMD: 40.67 -> 39.46 | Improved |
| interpolate the downsampled stream with PointINet | KITTI odometry point-cloud stream · KITTI odometry | Harris-3D repeatability: 0.155 -> 0.138 | Hurt |
| interpolate the downsampled stream with PointINet | KITTI odometry point-cloud stream · KITTI odometry | SIFT-3D repeatability: 0.174 -> 0.151 | Hurt |
Later papers that compared with this method
4 later accepted papers report PointINet as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- DiffPCI: Large Motion Point Cloud frame Interpolation with Diffusion Model (ICCV 2025 · better on 6 of 6 shared results)
- Dynamic 3D Point Cloud Sequences as 2D Videos (TPAMI 2024 · better on 2 of 2 shared results)
- NeuralPCI: Spatio-Temporal Neural Field for 3D Point Cloud Multi-Frame Non-Linear Interpolation (CVPR 2023 · better on 2 of 2 shared results)
- IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment (CVPR 2022 · better on 4 of 4 shared results)
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
- Dynamic 3D Scene Analysis by Point Cloud Accumulation (ECCV 2022 · similarity 0.87)
- LiDAR-Net: A Real-scanned 3D Point Cloud Dataset for Indoor Scenes (CVPR 2024 · similarity 0.87)
- LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures (AAAI 2026 · similarity 0.87)
- EINet: Point Cloud Completion via Extrapolation and Interpolation (ECCV 2024 · similarity 0.87)
- Learning Scene Dynamics from Point Cloud Sequences (IJCV 2022 · similarity 0.86)
- TULIP: Transformer for Upsampling of LiDAR Point Clouds (CVPR 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.
