VOCA: Boosting Visual Odometry Performance Using Codec Information
rsasaki0109 · x · 2026-08-03
Camera pose estimation via Visual Odometry (VO) is critical for spatial world models. However, traditional V-SLAM systems are mostly trained on raw, uncompressed videos, while real-world hardware relies on lossy compression that introduces visual artifacts hindering tracking.
Researchers introduced VOCA, a causal stereo visual-odometry method that exploits codec information to improve tracking. It achieves state-of-the-art performance for causal VO in terms of relative trajectory error, efficiency, and absolute trajectory error.
More from Embodied
- Wheeled vs. Bipedal: The Real Spatial Dilemma for Home Robots — carlosdponx · 2026-08-03
- Humanoid Robot Forecasts vs. Reality: Millions Predicted, Thousands Shipped — atShruti · 2026-08-03
- Open-Sourced by a 15-Year-Old: 3D-Printed Cycloidal Gearbox for Nema 17 — philfung · 2026-08-03
- Embodied AI Reaches Watershed: Real Deployment and Renewals Become New Valuation Standards — 量子位 · 2026-08-03
- AgenticROS Launches Cloud Service with Global P2P Teleop and Multi-Hardware Support — chrismatthieu · 2026-08-03
- N_0-VTLA: First VTLA Foundation Model Pretrained on Tactile Data at Scale — NeoteAIEmbodied · 2026-08-03