Research map / Probabilistic and scientific modeling / Variational and generative sampling
Information-Theoretic Odometry Learning
Sen Zhang, Jing Zhang, Dacheng Tao
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 information bottleneck objective to DeepVO (InfoVO) | DeepVO · KITTI | translation RMSE (m): 0.0658 -> 0.0607 | Improved |
| add information bottleneck objective to DeepVO (InfoVO) | DeepVO · KITTI | rotation RMSE (deg): 0.0942 -> 0.0869 | Improved |
| add information bottleneck objective to VINet (InfoVIO) | VINet · KITTI | rotation RMSE (deg): 0.0453 -> 0.0416 | Improved |
| add information bottleneck objective to VINet (InfoVIO) | VINet · EuRoC | rotation RMSE (deg): 0.0729 -> 0.0744 | No clear effect |
| add IB objective to DeepVO | DeepVO · vKITTI2 weather conditions | rotation RMSE (deg): 0.1676 -> 0.1368 | Improved |
| add IB objective to DeepVO | DeepVO · vKITTI2 weather conditions | translation RMSE (m): 1.5214 -> 1.5011 | Improved |
| add IB objective to DeepVO | DeepVO · vKITTI2 lighting conditions | translation RMSE (m): 1.4642 -> 1.3614 | Improved |
| add deterministic component to stochastic-only InfoVO (ablation) | InfoVO · KITTI | translation RMSE (m): 0.0758 -> 0.0607 | Improved |
| add deterministic component to stochastic-only InfoVIO (ablation) | InfoVIO · KITTI | rotation RMSE (deg): 0.0512 -> 0.0416 | Improved |
| increase IB weight gamma from 0.0 to 0.1 (ablation) | InfoVIO · EuRoC | rotation RMSE (deg): 0.0814 -> 0.0744 | Improved |
| increase IB weight gamma from 0.1 to 1.0 (ablation) | InfoVIO · KITTI | translation vs rotation RMSE: t 0.0580 -> 0.0648, r 0.0416 -> 0.0375 | Mixed |
| increase IB weight gamma from 0.1 to 1.0 (ablation) | InfoVIO · EuRoC | translation RMSE (m): 0.0276 -> 0.0873 | Hurt |
Closest papers by meaning
- Generalizing to the Open World: Deep Visual Odometry With Online Adaptation (CVPR 2021 · similarity 0.87)
- Information-Driven Direct RGB-D Odometry (CVPR 2020 · similarity 0.86)
- From Variance to Veracity: Unbundling and Mitigating Gradient Variance in Differentiable Bundle Adjustment Layers (CVPR 2024 · similarity 0.85)
- Adaptive VIO: Deep Visual-Inertial Odometry with Online Continual Learning (CVPR 2024 · similarity 0.84)
- EqNIO: Subequivariant Neural Inertial Odometry (ICLR 2025 · similarity 0.84)
- DiffLO: Semantic-Aware LiDAR Odometry with Diffusion-Based Refinement (CVPR 2025 · 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.
