Research map / Detection and segmentation / 3D detection and driving
LiDAR-Aug: A General Rendering-Based Augmentation Framework for 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 LiDAR-Aug rather than no object augmentation | SECOND · KITTI validation, Car hard | APCar70 (%): 68.44 -> 70.44 | Helped |
| add LiDAR-Aug rather than GT-Aug | PointRCNN · KITTI validation, Pedestrian hard | APPed50 (%): 50.53 -> 56.23 | Helped |
| use ValidMap placement instead of random placement (ablation) | LiDAR-Aug with PointRCNN · KITTI validation, Car easy | APCar70 (%): 79.11 -> 89.56 | Helped |
| use ValidMap placement instead of GT Pose (ablation) | LiDAR-Aug with PointRCNN · KITTI validation, Car moderate | APCar70 (%): 74.23 -> 79.51 | Helped |
| add collision avoidance (ablation) | LiDAR-Aug with PointRCNN and ValidMap poses · KITTI validation, Car easy | APCar70 (%): 87.14 -> 89.56 | Helped |
| add global augmentation (ablation) | PointRCNN without LiDAR-Aug · KITTI validation, Car easy | APCar70 (%): 85.34 -> 88.45 | Helped |
| combine global augmentation with LiDAR-Aug (ablation) | PointRCNN · KITTI validation, Car hard | APCar70 (%): 76.80 -> 77.89 | Helped |
| use synthetic objects instead of real objects (ablation) | PointRCNN training with real poses · KITTI validation, Car easy | APCar70 (%): 88.45 -> 76.73 | Hurt |
| use simulated poses instead of real poses (ablation) | PointRCNN training with real objects · KITTI validation, Car easy | APCar70 (%): 88.45 -> 88.05 | No clear effect |
| add LiDAR-Aug to global augmentation (ablation) | PointRCNN · KITTI validation, Car moderate | APCar70 (%): 77.67 -> 79.51 | Helped |
Closest papers by meaning
- Curricular Object Manipulation in LiDAR-Based Object Detection (CVPR 2023 · similarity 0.89)
- Beyond Virtual Points: Depth-Enhanced LiDAR-only 3D Object Detection with Semi-Supervised Learning (Student Abstract) (AAAI 2025 · similarity 0.88)
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection (CVPR 2025 · similarity 0.87)
- STONE: A Submodular Optimization Framework for Active 3D Object Detection (NeurIPS 2024 · similarity 0.87)
- iDet3D: Towards Efficient Interactive Object Detection for LiDAR Point Clouds (AAAI 2024 · similarity 0.87)
- Pre-training LiDAR-based 3D Object Detectors through Colorization (ICLR 2024 · similarity 0.87)
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.