Research map / 3D vision / Depth and stereo
SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments
Jongsung Lee, Gyeongsu Cho, Jeongin Park, Kyongjun Kim, Seongoh Lee, Jung-Hee Kim, Seong-Gyun Jeong, Kyungdon Joo
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 two-step classification plus residual regression for slanted angle instead of regression only (ablation) | SlaBins · SynWoodScape | Abs Rel: 0.075 -> 0.022 | Improved |
| use two-step angle prediction instead of classification only (ablation) | SlaBins · SynWoodScape | Abs Rel: 0.026 -> 0.022 | Improved |
| use two-step angle prediction instead of regression only (ablation) | SlaBins · KITTI-360 depth | Abs Rel: 0.604 -> 0.077 | Improved |
| use slanted multi-cylindrical image representation with orthogonal bins on top of AdaBins-style bins | AdaBins · SynWoodScape | RMSE: 1.524 -> 1.040 | Improved |
| use SlaBins versus AdaBins on KITTI-360 depth | fisheye depth · KITTI-360 depth | RMSE: 1.590 -> 1.537 | Improved |
| use SlaBins versus AdaBins on KITTI-360 depth | fisheye depth · KITTI-360 depth | Abs Rel: 0.074 -> 0.077 | No clear effect |
Closest papers by meaning
- MGNet: Monocular Geometric Scene Understanding for Autonomous Driving (ICCV 2021 · similarity 0.87)
- Towards Robust Driving Perception: A Flexible Scale-Driven Family for Self-Supervised Monocular Depth Estimation (ECCV 2026 · similarity 0.86)
- Single View Stereo Matching (CVPR 2018 · similarity 0.86)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.85)
- Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving (CVPR 2024 · similarity 0.85)
- Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation (NeurIPS 2024 · similarity 0.85)
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.
