Research map / 3D vision / Depth and stereo
VOCA: Visual Odometry with Codec Awareness
Nouri Alexander Hilscher, Mateo de Mayo, Dominik Muhle, Christoph Otten genannt Hermes, Daniel Cremers
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 |
|---|---|---|---|
| initialize KLT tracking with codec motion vectors and add I-frame bridging (full VOCA vs Basalt) | Basalt · EuRoC | AVG RTE (cm): 1.947 -> 1.669 | Improved |
| add codec motion-vector priors to Basalt | Basalt · TUM-VI room | AVG ATE (cm): 20.34 -> 9.64 | Improved |
| add codec motion-vector priors to Basalt | Basalt · TUM-VI room | AVG RTE (cm): 2.820 -> 0.815 | Improved |
| add codec motion-vector priors to Basalt | Basalt · Monado SLAM Dataset | median ATE (cm): 479.20 -> 78.30 | Improved |
| add codec motion-vector priors to Basalt | Basalt · Monado SLAM Dataset | ATE success rate (%): 34.4% -> 46.9% | Improved |
| use parallel MV||OF with consistency filtering (C) instead of OF-then-MV fallback (A) (ablation) | VOCA · TUM-VI room | AVG RTE (cm): 1.380 -> 0.919 | Improved |
| use parallel MV||OF (C) instead of MV-then-OF (B) (ablation) | VOCA · EuRoC | AVG RTE (cm): 2.044 -> 1.710 | Improved |
| add I-frame bridging to MV||OF (ablation) | VOCA (C) · TUM-VI room | AVG RTE (cm): 0.919 -> 0.829 | Improved |
| add I-frame bridging to MV||OF (ablation) | VOCA (C) · TUM-VI room | median ATE (cm): 8.90 -> 7.40 | Improved |
| add I-frame bridging to MV||OF (ablation) | VOCA (C) · EuRoC | AVG ATE (cm): 18.70 -> 18.00 | No clear effect |
| add codec motion-vector priors with tracking-with-and-without-prior filtering vs Basalt | Basalt · EuRoC | median ATE (cm): 20.00 -> 17.50 | Improved |
Later papers that compared with this method
1 later accepted paper reports VOCA as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Beyond Fixed Topologies: Unregistered Training and Comprehensive Evaluation Metrics for 3D Talking Heads (IJCV 2026 · better on 4 of 4 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry (CVPR 2024 · similarity 0.88)
- Deep Visual Odometry With Adaptive Memory (TPAMI 2020 · similarity 0.88)
- Modality-Invariant Visual Odometry for Embodied Vision (CVPR 2023 · similarity 0.88)
- MBA-VO: Motion Blur Aware Visual Odometry (ICCV 2021 · similarity 0.87)
- ZeroVO: Visual Odometry with Minimal Assumptions (CVPR 2025 · similarity 0.85)
- Leveraging Consistent Spatio-Temporal Correspondence for Robust Visual Odometry (AAAI 2025 · 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.
