Research map / Detection and segmentation / 3D detection and driving
GUIDE: Gaussian Unified Instance Detection for Enhanced Obstacle Perception in Autonomous Driving
Chunyong Hu, Qi Luo, Jianyun Xu, Song Wang, Qiang Li, Sheng Yang
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 |
|---|---|---|---|
| increase Gaussians per instance from 16 to 48 (ablation) | GUIDE · nuScenes val | mAP_occ (10 classes): 18.94 -> 22.81 | Improved |
| increase Gaussians per instance from 16 to 48 (ablation) | GUIDE · nuScenes val | mIoU: 22.79 -> 25.39 | Improved |
| increase Gaussians per instance from 16 to 48 (ablation) | GUIDE · nuScenes val | latency: 205ms -> 373ms | Hurt |
| increase Gaussians per instance from 16 to 48 (ablation) | GUIDE · nuScenes val | GPU memory: 2926 MB -> 3434 MB | Hurt |
| add instance bank (temporal fusion) (ablation) | GUIDE · nuScenes val | mAP_occ (10 classes): 16.42 -> 22.81 | Improved |
| add instance bank (temporal fusion) (ablation) | GUIDE · nuScenes val | mIoU (10 fg classes): 21.51 -> 25.39 | Improved |
| increase candidate instances from 300 to 900 (ablation) | GUIDE · nuScenes val | mAP_occ (10 classes): 18.94 -> 22.81 | Improved |
| increase candidate instances from 300 to 900 (ablation) | GUIDE · nuScenes val | mIoU (10 fg classes): 22.68 -> 25.39 | Improved |
| use instance Gaussian representation instead of SparseOcc | GUIDE · nuScenes val | mAP_occ (8 classes): 14.40 -> 21.61 | Improved |
| use instance Gaussian representation instead of SparseOcc | GUIDE · nuScenes val | GPU memory: 5424 MB -> 3434 MB | Improved |
| use instance Gaussians instead of SparseOcc for tracking | GUIDE vs SparseDrive-S · nuScenes val | IDS: 886 -> 516 | Improved |
| GUIDE vs SparseOcc on barriers and traffic cones | GUIDE · nuScenes val (barrier, traffic cone) | mIoU: 28.99 -> 30.96 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- BevFormer — BEVFormer: Learning Bird’s-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers (ECCV 2022) · better on 0 of 2 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
- GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction (CVPR 2025 · similarity 0.90)
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 2025 · similarity 0.90)
- GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction (CVPR 2025 · similarity 0.89)
- SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- GaussianFusion: Gaussian-Based Multi-Sensor Fusion for End-to-End Autonomous Driving (NeurIPS 2025 · similarity 0.88)
- QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction (NeurIPS 2025 · similarity 0.88)
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.
