Research map / Optimization / Optimizers
TESO: Online Tracking of Essential Matrix by Stochastic Optimization
Jaroslav Moravec, Radim Sara, Akihiro Sugimoto
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 TESO tracking | stereo rectification · CARLA-Drift | Rx error (deg): 0.157 -> 0.011 | Improved |
| add TESO tracking | stereo rectification · CARLA-Drift | Ry error (deg): 0.166 -> 0.039 | Improved |
| add TESO tracking | stereo rectification · CARLA-Drift | KO-I (px): 1.94 -> 0.03 | Improved |
| add TESO tracking | stereo rectification · CARLA-Drift | DC-I (m): 2.06 -> 0.52 | Improved |
| use recalibrated intrinsics from prior work | TESO on KITTI pair 00-01 · KITTI stereo 00-01 | Ry error (deg): 0.489 -> 0.025 | Improved |
| add 0.01 deg per-frame drift to MAN data | TESO · MAN TruckScenes | Ry error (deg): 0.115 -> 0.126 | Hurt |
| use SIFT instead of ORB keypoints (ablation) | TESO · CARLA-Drift | Average rotational error (deg): 0.037 -> 0.022 | Improved |
| use SIFT instead of BRISK keypoints (ablation) | TESO · CARLA-Drift | Average rotational error (deg): 0.022 -> 0.022 | No clear effect |
| use kernelized DE optimization vs end-to-end learned best method | TESO kernel error · CARLA-FlowGuided | Ry error (deg): 0.077 -> 0.027 | Improved |
| use kernelized DE optimization vs best learned method | TESO kernel error · CARLA-FlowGuided | DC (m): 3.2 -> 4.6 | Hurt |
Closest papers by meaning
- Rectification-specific Supervision and Constrained Estimator for Online Stereo Rectification (CVPR 2025 · similarity 0.87)
- Flow-Guided Online Stereo Rectification for Wide Baseline Stereo (CVPR 2024 · similarity 0.86)
- Beyond Row Alignment: Virtual-Camera-Aware Online Stereo Rectification (NeurIPS 2026 · similarity 0.85)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.84)
- PPMStereo: Pick-and-Play Memory Construction for Consistent Dynamic Stereo Matching (NeurIPS 2025 · similarity 0.83)
- Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving (CVPR 2024 · similarity 0.83)
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.
