Research map / Probabilistic and scientific modeling / Molecules and proteins
S2Net: Stochastic Sequential Pointcloud Forecasting
Xinshuo Weng, Junyu Nan, Kuan-Hui Lee, Rowan McAllister, Adrien Gaidon, Nicholas Rhinehart, Kris M. Kitani
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 pyramid LSTMs | S2Net · KITTI raw test, 1s horizon | CD: 0.341 -> 0.203 | Improved |
| add temporally-dependent latent space | S2Net · KITTI raw test, 1s horizon | CD: 0.203 -> 0.148 | Improved |
| add temporally-dependent latent space | S2Net · KITTI raw test, 3s horizon | CD: 0.360 -> 0.293 | Improved |
| add temporally-dependent latent space | S2Net · nuScenes test, 1s horizon | CD: 0.366 -> 0.321 | Improved |
| add temporally-dependent latent space | S2Net · nuScenes test, 3s horizon | EMD: 205.269 -> 209.267 | Hurt |
| use direct latent dependency instead of none (ablation) | S2Net · KITTI raw test, 1s horizon | CD: 0.171 -> 0.148 | Improved |
| use direct latent dependency instead of none (ablation) | S2Net · KITTI raw test, 3s horizon | CD: 0.357 -> 0.293 | Improved |
| use direct latent dependency instead of indirect (ablation) | S2Net · nuScenes test, 3s horizon | CD: 0.482 -> 0.381 | Improved |
| use direct latent dependency instead of indirect (ablation) | S2Net · KITTI raw test, 1s horizon | EMD: 92.586 -> 84.418 | Improved |
| add pyramid LSTMs with L=7 instead of none (ablation) | S2Net · KITTI raw test, 1s horizon | CD: 0.366 -> 0.148 | Improved |
| add pyramid LSTMs with L=7 instead of none (ablation) | S2Net · KITTI raw test, 3s horizon | CD: 0.472 -> 0.293 | Improved |
| increase pyramid levels from 1 to 7 (ablation) | S2Net · KITTI raw test, 1s horizon | CD: 0.196 -> 0.148 | Improved |
Closest papers by meaning
- Visual Point Cloud Forecasting enables Scalable Autonomous Driving (CVPR 2024 · similarity 0.87)
- SmartPretrain: Model-Agnostic and Dataset-Agnostic Representation Learning for Motion Prediction (ICLR 2025 · similarity 0.87)
- Motion Forecasting in Continuous Driving (NeurIPS 2024 · similarity 0.87)
- 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 0.86)
- SEPT: Towards Efficient Scene Representation Learning for Motion Prediction (ICLR 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.
