Research map / 3D vision / 3D generation
SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping Using Monocular Frontal View Images
Nikhil Gosala, Kürsat Petek, Paulo L. J. Drews-Jr, Wolfram Burgard, Abhinav Valada
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 |
|---|---|---|---|
| Use SkyEye instead of PoBEV | BEV semantic mapping · KITTI-360 | mIoU: 30.42 -> 30.49 | No clear effect |
| Use SkyEye instead of PoBEV | Models pretrained on KITTI-360 · Waymo validation | mIoU: 16.94 -> 22.57 | Improved |
| Add implicit supervision (ablation) | SkyEye with 0.1% BEV pseudolabels · KITTI-360 | mIoU: 15.22 -> 22.71 | Improved |
| Add implicit supervision (ablation) | SkyEye with 1% BEV pseudolabels · KITTI-360 | mIoU: 21.06 -> 28.15 | Improved |
| Add implicit supervision (ablation) | SkyEye with 10% BEV pseudolabels · KITTI-360 | mIoU: 28.46 -> 29.88 | Improved |
| Add implicit supervision (ablation) | SkyEye with 50% BEV pseudolabels · KITTI-360 | mIoU: 29.64 -> 30.55 | Improved |
| Add implicit supervision (ablation) | SkyEye with 100% BEV pseudolabels · KITTI-360 | mIoU: 30.23 -> 30.49 | Improved |
| Add frame accumulation to pseudolabel generation (ablation) | SkyEye · KITTI-360 | mIoU: 23.26 -> 30.49 | Improved |
| Use depth-based lifting instead of IPM for pseudolabel creation (ablation) | SkyEye · KITTI-360 | mIoU: 25.57 -> 30.49 | Improved |
| Add clustering and bounding-box fitting for dynamic objects (ablation) | SkyEye pseudolabel generation · KITTI-360 | Car IoU: 29.96 -> 32.73 | Improved |
| Add bounding-box fitting for dynamic objects (ablation) | SkyEye pseudolabel generation · KITTI-360 | Car IoU: 25.95 -> 32.73 | Improved |
| Use window size 10 instead of window size 6 (ablation) | SkyEye implicit supervision with 1% BEV pseudolabels · KITTI-360 | mIoU: 28.03 -> 28.15 | Improved |
Later papers that compared with this method
2 later accepted papers report SkyEye as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets (NeurIPS 2024 · better on 2 of 4 shared results)
- LetsMap: Unsupervised Representation Learning for Label-Efficient Semantic BEV Mapping (ECCV 2024 · better on 1 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
- Improving Bird's Eye View Semantic Segmentation by Task Decomposition (CVPR 2024 · similarity 0.89)
- Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets (NeurIPS 2024 · similarity 0.87)
- A Black-Box Evaluation Framework for Semantic Robustness in Bird’s Eye View Detection (AAAI 2025 · similarity 0.87)
- Self-Supervised Bird’s Eye View Motion Prediction with Cross-Modality Signals (AAAI 2024 · similarity 0.86)
- VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization (NeurIPS 2024 · similarity 0.86)
- MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations (ICLR 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.
