VOCA: Visual Odometry with Codec Awareness
2026-06-30 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on figuring out where a camera is positioned and how it moves by looking at video streams. Most current methods assume videos are raw and uncompressed, but many real systems use compressed videos that lose some quality and make tracking harder. They introduce VOCA, a new method that uses information from the video compression process to better track the camera’s movement despite these quality losses. Their approach works well and improves accuracy and speed on compressed videos. This shows that using details from video codecs can help with camera tracking tasks.
camera pose estimationvisual odometrysimultaneous localization and mappingvideo compressioncodectrajectory errorstereo visiontrackingcausal methodvisual artifacts
Authors
Nouri Alexander Hilscher, Mateo de Mayo, Dominik Muhle, Christoph Otten genannt Hermes, Daniel Cremers
Abstract
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.