Research map / 3D vision / Depth and stereo
D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 photometric uncertainty estimation (ablation) | D3VO depth network · KITTI Eigen split | RMSE: 4.650 -> 4.485 | Helped |
| Add predictive brightness transformation (ablation) | D3VO depth network · KITTI Eigen split | RMSE: 4.532 -> 4.485 | Helped |
| Add predictive brightness transformation (ablation) | D3VO depth network · EuRoC V2_01 | RMSE: 0.368 -> 0.337 | Helped |
| Add photometric uncertainty estimation (ablation) | D3VO depth network · EuRoC V2_01 | RMSE: 0.339 -> 0.337 | Helped |
| Add brightness transformation predicted by PoseNet (ablation) | Photometric alignment on EuRoC V2_03_difficult · EuRoC V2_03_difficult | average photometric error: 0.10 -> 0.03 | Helped |
| Use PoseNet-predicted rather than least-squares brightness parameters (ablation) | Photometric alignment on EuRoC V2_03_difficult · EuRoC V2_03_difficult | average photometric error: 0.07 -> 0.03 | Helped |
| Add deep uncertainty weighting (ablation) | D3VO visual odometry · KITTI Odometry test split | t_rel mean: 0.88 -> 0.84 | Helped |
| Add deep pose estimation (ablation) | D3VO visual odometry · KITTI Odometry test split | t_rel mean: 0.88 -> 0.87 | Helped |
| Add deep pose estimation (ablation) | D3VO visual odometry · EuRoC MAV | ATE RMSE mean: 0.29 -> 0.11 | Helped |
| Add deep uncertainty weighting (ablation) | D3VO visual odometry · EuRoC MAV | ATE RMSE mean: 0.11 -> 0.10 | Helped |
Closest papers by meaning
- Unsupervised Learning of Monocular Depth Estimation and Visual Odometry With Deep Feature Reconstruction (CVPR 2018 · similarity 0.92)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.89)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.88)
- ZeroVO: Visual Odometry with Minimal Assumptions (CVPR 2025 · similarity 0.87)
- MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothing (CVPR 2025 · similarity 0.87)
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (CVPR 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.