VOCA: Visual Odometry with Codec Awareness

2026-06-30

AI Summary

This work addresses the significant performance degradation of traditional visual odometry when processing hardware-compressed video, primarily caused by compression artifacts. To mitigate this issue, the authors propose a novel causal stereo visual odometry method that explicitly incorporates video codec information into the pose estimation pipeline for the first time. By leveraging compression-domain feature compensation and codec-aware modeling, the approach effectively alleviates the adverse effects of compression-induced distortions. While maintaining strict causality, the method jointly optimizes both relative and absolute trajectory errors, achieving state-of-the-art accuracy and robustness on compressed video streams. Experimental results demonstrate substantial improvements over existing approaches, all while preserving computational efficiency.

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.

Problem

• Visual Odometry
• Video Compression
• Codec Artifacts
• Pose Estimation
• Compressed Video Streams

Innovation

• Visual Odometry
• Codec Awareness
• Compressed Video
• Causal Tracking
• Stereo Vision