Research map / Detection and segmentation / CNN features
SimVODIS: Simultaneous Visual Odometry, Object Detection, and Instance Segmentation
Ue-Hwan Kim, Se-Ho Kim, Jong-Hwan Kim
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 automasking (ablation) | SimVODIS · KITTI depth | ARD: 0.129 -> 0.123 | Improved |
| add min. loss (ablation) | SimVODIS · KITTI depth | ARD: 0.127 -> 0.123 | Improved |
| add SSIM loss (ablation) | SimVODIS · KITTI depth | ARD: 0.136 -> 0.123 | Improved |
| add SSIM loss (ablation) | SimVODIS · KITTI pose Seq. 09 | ATE: 0.017 -> 0.012 | Improved |
| add automasking (ablation) | SimVODIS · KITTI pose Seq. 09 | ATE: 0.019 -> 0.012 | Improved |
| use full-size input instead of 416x128 (ablation) | SimVODIS · KITTI depth | RMSE: 4.976 -> 4.727 | Improved |
| use 4 scales instead of the default (ablation) | SimVODIS · KITTI depth | ARD: 0.126 vs 0.123 | Hurt |
| train on more heterogeneous datasets (all vs KITTI only) | SimVODIS · KITTI depth | ARD: 0.123 -> 0.203 | Hurt |
| train on more heterogeneous datasets (all vs KITTI only) | SimVODIS · Make3D depth | ARD: 0.392 -> 0.367 | Improved |
| train on RGB-D data only instead of all data | SimVODIS · RGB-D SLAM indoor depth | ARD: 0.339 -> 0.285 | Improved |
| compare unsupervised SimVODIS to Godard et al. | SimVODIS · KITTI depth | SRD: 0.903 -> 0.797 | Improved |
Closest papers by meaning
- PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation (ECCV 2026 · similarity 0.86)
- ClusterVO: Clustering Moving Instances and Estimating Visual Odometry for Self and Surroundings (CVPR 2020 · similarity 0.86)
- ZeroVO: Visual Odometry with Minimal Assumptions (CVPR 2025 · similarity 0.85)
- OVOD-Agent: A Markov-Bandit Framework for Proactive Visual Reasoning and Self-Evolving Detection (CVPR 2026 · similarity 0.83)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · similarity 0.83)
- CorrBEV: Multi-View 3D Object Detection by Correlation Learning with Multi-modal Prototypes (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.
