Search papers, labs, and topics across Lattice.
The paper introduces FreqTrack, a novel RGB-Event object tracking framework that leverages frequency-domain transformations to fuse RGB and event data. It uses a Spectral Enhancement Transformer (SET) layer with dynamic Fourier filtering to adaptively enhance frequency-domain features and a Wavelet Edge Refinement (WER) module to extract multi-scale edge structures from event data. Experiments on COESOT and FE108 datasets show FreqTrack achieves state-of-the-art performance, demonstrating the effectiveness of frequency-domain modeling for RGBE tracking.
Frequency-domain fusion of RGB and event data significantly boosts object tracking performance, achieving a leading 76.6% precision on the challenging COESOT benchmark.
Existing single-modal RGB trackers often face performance bottlenecks in complex dynamic scenes, while the introduction of event sensors offers new potential for enhancing tracking capabilities. However, most current RGB-event fusion methods, primarily designed in the spatial domain using convolutional, Transformer, or Mamba architectures, fail to fully exploit the unique temporal response and high-frequency characteristics of event data. To address this, we1 propose FreqTrack, a frequency-aware RGBE tracking framework that establishes complementary inter-modal correlations through frequency-domain transformations for more robust feature fusion. We design a Spectral Enhancement Transformer (SET) layer that incorporates multi-head dynamic Fourier filtering to adaptively enhance and select frequency-domain features. Additionally, we develop a Wavelet Edge Refinement (WER) module, which leverages learnable wavelet transforms to explicitly extract multi-scale edge structures from event data, effectively improving modeling capability in high-speed and low-light scenarios. Extensive experiments on the COESOT and FE108 datasets demonstrate that FreqTrack achieves highly competitive performance, particularly attaining leading precision of 76.6\% on the COESOT benchmark, validating the effectiveness of frequency-domain modeling for RGBE tracking.
