Research map / Point clouds / Point cloud classification
TPCN: Temporal Point Cloud Networks for Motion Forecasting
Maosheng Ye, Tongyi Cao, Qifeng Chen
Check 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 dual point-voxel spatial learning (ablation) | TPCN · Argoverse validation | minADE₁: 1.63 -> 1.50 | Improved |
| add Multi-interval Learning (ablation) | TPCN · Argoverse validation | minADE₁: 1.50 -> 1.38 | Improved |
| add Instance Pooling (ablation) | TPCN · Argoverse validation | minADE₁: 1.38 -> 1.36 | Improved |
| add data augmentation (ablation) | TPCN · Argoverse validation | minADE₁: 1.36 -> 1.34 | Improved |
| use displacement regression rather than classification loss (ablation) | TPCN · Argoverse validation | minADE₁: 1.44 -> 1.34 | Improved |
| use displacement regression rather than classification loss (ablation) | TPCN · Argoverse validation | minADE₆: 0.74 -> 0.73 | No clear effect |
| include other agents and map data (ablation) | TPCN · Argoverse validation | minADE₁: 2.53 -> 1.34 | Improved |
| expand MIL intervals from [2, 4, 6] to [2, 4, 6, 8, 16] (ablation) | TPCN · Argoverse validation | minADE₁: 1.43 -> 1.34 | Improved |
| use learned uncertain-loss weighting (ablation) | TPCN · Argoverse validation | minADE | Hurt |
| jointly propagate spatial and temporal features | TPCN · Argoverse test | minADE₁: 1.66 vs 1.71 | Improved |
Closest papers by meaning
- Spatial-Temporal Consistency Network for Low-Latency Trajectory Forecasting (ICCV 2021 · similarity 0.88)
- S2Net: Stochastic Sequential Pointcloud Forecasting (ECCV 2022 · similarity 0.88)
- RAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting (ICCV 2021 · similarity 0.87)
- MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction (NeurIPS 2026 · similarity 0.86)
- HPNet: Dynamic Trajectory Forecasting with Historical Prediction Attention (CVPR 2024 · similarity 0.86)
- Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations (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.
