VOCA: Visual Odometry with Codec Awareness
This work addresses the problem of degraded visual odometry performance on compressed video streams, which is common in real-world systems using hardware codecs.
VOCA introduces a causal stereo visual-odometry method that leverages video codec information to improve tracking on compressed video streams, achieving state-of-the-art performance in relative trajectory error, efficiency, and absolute trajectory error.
Camera pose estimation from image streams is a critical component of spatial world models that integrate perception into planning and decision-making. Nearly all Visual Odometry (VO) and Simultaneous Localization and Mapping (V-SLAM) systems have focused on datasets containing raw, uncompressed videos. Many working systems instead use ubiquitous hardware units to efficiently compress and decode video streams, saving orders of magnitude in storage and bandwidth. However, this lossy compression introduces visual artifacts that hinder the performance of traditional tracking systems. We present VOCA, a causal stereo visual-odometry method that exploits codec information to improve tracking performance. We achieve state-of-the-art performance on causal VO for relative trajectory error, efficiency, and absolute trajectory error on compressed streams. This work highlights the potential of leveraging widely available video codec information for vision tasks.