Research map / Detection and segmentation / 3D detection and driving
RSN: Range Sparse Net for Efficient, Accurate LiDAR 3D Object Detection
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 range image features (ablation) | RSN CarS_3f · Waymo Open Dataset validation, vehicle | APH L2 3D: 59.7 -> 63.9 | Helped |
| add range image features (ablation) | RSN PedS_3f · Waymo Open Dataset validation, pedestrian | APH L2 3D: 60.5 -> 66.07 | Helped |
| train end-to-end so SPFE gradients reach RIFE (ablation) | RSN CarS_3f · Waymo Open Dataset validation, vehicle | APH L2 3D: 59.7 -> 63.9 | Helped |
| train end-to-end so SPFE gradients reach RIFE (ablation) | RSN PedS_3f · Waymo Open Dataset validation, pedestrian | APH L2 3D: 61.7 -> 66.07 | Helped |
| add ego-motion-corrected temporal xyz features (ablation) | RSN CarS_3f · Waymo Open Dataset validation, vehicle | APH L2 3D: 63.9 -> 63.7 | No clear effect |
| add ego-motion-corrected temporal xyz features (ablation) | RSN PedS_3f · Waymo Open Dataset validation, pedestrian | APH L2 3D: 66.07 -> 61.3 | Hurt |
| enable heatmap normalization (ablation) | RSN CarS_3f · Waymo Open Dataset validation, vehicle | APH L2 3D: 60.2 -> 63.9 | Helped |
| enable heatmap normalization (ablation) | RSN PedS_3f · Waymo Open Dataset validation, pedestrian | APH L2 3D: 61.9 -> 66.07 | Helped |
| add three-frame temporal input instead of single-frame input | RSN CarS · Waymo Open Dataset validation, vehicle | APH L1 3D: 70.0 -> 74.4 | Helped |
| add three-frame temporal input instead of single-frame input | RSN PedS · Waymo Open Dataset validation, pedestrian | APH L1 3D: 69.6 -> 75.2 | Helped |
| remove RIFE and foreground point selection (ablation) | RSN CarS_3f · Internal long-range LiDAR test, vehicle | 3D APH: 61.2 -> 53.4 | Hurt |
Closest papers by meaning
- SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection (CVPR 2024 · similarity 0.90)
- LaserNet: An Efficient Probabilistic 3D Object Detector for Autonomous Driving (CVPR 2019 · similarity 0.89)
- Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images (NeurIPS 2022 · similarity 0.89)
- FSHNet: Fully Sparse Hybrid Network for 3D Object Detection (CVPR 2025 · similarity 0.87)
- LION: Linear Group RNN for 3D Object Detection in Point Clouds (NeurIPS 2024 · similarity 0.87)
- ViKIENet: Towards Efficient 3D Object Detection with Virtual Key Instance Enhanced Network (CVPR 2025 · similarity 0.86)
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.