AV1 Motion Vector Fidelity and Application for Efficient Optical Flow
By: Julien Zouein, Vibhoothi Vibhoothi, Anil Kokaram
Potential Business Impact:
Speeds up video analysis by using existing motion data.
This paper presents a comprehensive analysis of motion vectors extracted from AV1-encoded video streams and their application in accelerating optical flow estimation. We demonstrate that motion vectors from AV1 video codec can serve as a high-quality and computationally efficient substitute for traditional optical flow, a critical but often resource-intensive component in many computer vision pipelines. Our primary contributions are twofold. First, we provide a detailed comparison of motion vectors from both AV1 and HEVC against ground-truth optical flow, establishing their fidelity. In particular we show the impact of encoder settings on motion estimation fidelity and make recommendations about the optimal settings. Second, we show that using these extracted AV1 motion vectors as a "warm-start" for a state-of-the-art deep learning-based optical flow method, RAFT, significantly reduces the time to convergence while achieving comparable accuracy. Specifically, we observe a four-fold speedup in computation time with only a minor trade- off in end-point error. These findings underscore the potential of reusing motion vectors from compressed video as a practical and efficient method for a wide range of motion-aware computer vision applications.
Similar Papers
Leveraging AV1 motion vectors for Fast and Dense Feature Matching
CV and Pattern Recognition
Finds matching spots in videos with less computer power.
Leveraging AV1 motion vectors for Fast and Dense Feature Matching
CV and Pattern Recognition
Finds matching points in videos faster, using less power.
Temporal Realism Evaluation of Generated Videos Using Compressed-Domain Motion Vectors
CV and Pattern Recognition
Makes AI videos move more like real life.