Enhancing Fourier-Based Doppler Resolution with Diffusion Models

In radar systems, high resolution in the Doppler dimension is important for detecting slow-moving targets as it allows for more distinct separation between these targets and clutter, or stationary objects. However, achieving sufficient resolution is con-strained by hardware capabilities and physical factors, leading to the development of processing techniques to enhance the resolution after acquisition. In this work, we lever-age artificial intelligence to increase the Doppler resolution in range-Doppler maps. Based on a zero-padded FFT, a refinement via the generative neural networks of diffu-sion models is achieved. We demonstrate that our method overcomes the limitations of traditional FFT, generating data where closely spaced targets are effectively separated.