DiffUFlow: Robust fine-grained urban flow inference with denoising diffusion model

Inferring the fine-grained urban flows based on the coarse-grained flow observations is practically important to many smart city-related applications. However, the collected urban flows are usually rather unreliable, may contain noise and sometimes are incomplete, thus posing great challenges to existing approaches. In this paper, we present a pioneering study on robust fine-grained urban flow inference with noisy and incomplete urban flow observations, and propose a denoising diffusion model named DiffUFlow to effectively address it with an improved reverse diffusion strategy. Specifically, a spatial-temporal feature extraction network called STFormer and a semantic features extraction network called ELFetcher are proposed. Then, we overlay the extracted spatial-temporal feature map onto the coarse-grained flow map, serving as a conditional guidance for the reverse diffusion process. We further integrate the semantic features extracted by ELFetcher to cross-attention layers, enabling the comprehensive consideration of semantic information for fine-grained flow inference. Extensive experiments on two large real-world datasets validate the effectiveness of our method compared with the state-of-the-art baselines. Copyright © 2023 held by the owner/author(s). Publication rights licensed to ACM.