Research map / Detection and segmentation / 3D detection and driving
Eliminating the Blind Spot: Adapting 3D Object Detection and Monocular Depth Estimation to 360° Panoramic Imagery
Greire Payen de La Garanderie, Amir Atapour Abarghouei, Toby P. Breckon
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 projection transformation to training data (ablation) | 3D detector · CARLA panoramic | mAP: 0.336 -> 0.244 | Hurt |
| add style transfer from Mapillary and CARLA combined (ablation) | 3D detector · CARLA panoramic | mAP: 0.336 -> 0.378 | Improved |
| add style transfer from CARLA only (ablation) | 3D detector · CARLA panoramic | mAP: 0.336 -> 0.355 | Improved |
| add style transfer from Mapillary only (ablation) | 3D detector · CARLA panoramic | mAP: 0.336 -> 0.359 | Improved |
| add projection transformation to style M+C training data (ablation) | 3D detector · CARLA panoramic | mAP: 0.378 -> 0.344 | Hurt |
| add projection transformation to training data for depth (ablation) | Monocular depth · CARLA panoramic depth | delta<1.25 accuracy: 0.697 -> 0.732 | Improved |
| add style transfer from CARLA to depth training data (ablation) | Monocular depth · CARLA panoramic depth | delta<1.25 accuracy: 0.697 -> 0.686 | Hurt |
| add style transfer from Mapillary and CARLA to depth training data (ablation) | Monocular depth · CARLA panoramic depth | Abs. rel.: 0.247 -> 0.230 | Improved |
| add projection transformation on top of style C for depth (ablation) | Monocular depth · CARLA panoramic depth | Abs. rel.: 0.262 -> 0.292 | Hurt |
| train detector on CARLA-adapted data, test on real CARLA instead of adapted images | 3D detector · CARLA panoramic | mAP: 0.82 -> 0.35 | Hurt |
| replace zero-padding with horizontal ring-padding (ablation) | Panoramic detector and depth network · Mapillary panoramas (qualitative) | boundary detection and depth continuity | Improved |
Closest papers by meaning
- A Depth Complementary Framework for Monocular 3D Object Detection in Autonomous Driving (TPAMI 2026 · similarity 0.87)
- Monocular 3D Object Detection: An Extrinsic Parameter Free Approach (CVPR 2021 · similarity 0.87)
- Distortion-Aware Convolutional Filters for Dense Prediction in Panoramic Images (ECCV 2018 · similarity 0.87)
- CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography (CVPR 2026 · similarity 0.87)
- Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation (ECCV 2026 · similarity 0.87)
- IDA-3D: Instance-Depth-Aware 3D Object Detection From Stereo Vision for Autonomous Driving (CVPR 2020 · 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.
