Frame-event alignment and fusion network for high frame rate tracking

J Zhang, Y Wang, W Liu, M Li, J Bai… - Proceedings of the …, 2023 - openaccess.thecvf.com
Most existing RGB-based trackers target low frame rate benchmarks of around 30 frames
per second. This setting restricts the tracker's functionality in the real world, especially for fast
motion. Event-based cameras as bioinspired sensors provide considerable potential for high
frame rate tracking due to their high temporal resolution. However, event-based cameras
cannot offer fine-grained texture information like conventional cameras. This unique
complementarity motivates us to combine conventional frames and events for high frame …

[PDF][PDF] Frame-Event Alignment and Fusion Network for High Frame Rate Tracking (Supplementary Material)

J Zhang, Y Wang, W Liu, M Li, J Bai, B Yin, X Yang - openaccess.thecvf.com
In this Supplemental Material, we present additional analyses and qualitative results in
support of the findings from the main paper. In section 1, we provide a comparison of single-
modality with multi-modality under different challenging conditions. Next, section 2 provides
additional visual examples from the VisEvent [5] dataset. Section 3 analyzes whether our
fusion module can be replaced by lightweight models. Next, section 4 provides qualitative
results from the video interpolation method SuperSloMo [3] to analyze why interpolation on …
以上显示的是最相近的搜索结果。 查看全部搜索结果