Papers › UrbanFM: Inferring Fine-Grained Urban Flows

UrbanFM: Inferring Fine-Grained Urban Flows

6 Feb 2019arXiv:1902.05377archive 2025-07-28

Yuxuan Liang, Kun Ouyang, Lin Jing, Sijie Ruan, Ye Liu, Junbo Zhang, David S. Rosenblum, Yu Zheng

Urban flow monitoring systems play important roles in smart city efforts around the world. However, the ubiquitous deployment of monitoring devices, such as CCTVs, induces a long-lasting and enormous cost for maintenance and operation. This suggests the need for a technology that can reduce the number of deployed devices, while preventing the degeneration of data accuracy and granularity. In this paper, we aim to infer the real-time and fine-grained crowd flows throughout a city based on coarse-grained observations. This task is challenging due to two reasons: the spatial correlations between coarse- and fine-grained urban flows, and the complexities of external impacts. To tackle these issues, we develop a method entitled UrbanFM based on deep neural networks. Our model consists of two major parts: 1) an inference network to generate fine-grained flow distributions from coarse-grained inputs by using a feature extraction module and a novel distributional upsampling module; 2) a general fusion subnet to further boost the performance by considering the influences of different external factors. Extensive experiments on two real-world datasets, namely TaxiBJ and HappyValley, validate the effectiveness and efficiency of our method compared to seven baselines, demonstrating the state-of-the-art performance of our approach on the fine-grained urban flow inference problem.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

yoshall/UrbanFM officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Fine-Grained Urban Flow Inference

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fine-Grained Urban Flow Inference TaxiBJ-P1 UrbanFM MAE 2.011 #2 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 UrbanFM MAPE 0.327 #2 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 UrbanFM MSE 15.6025 #2 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 UrbanFM-ne MAE 2.047 #3 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 UrbanFM-ne MAPE 0.332 #3 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 UrbanFM-ne MSE 16.1202 #3 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 DeepSD MAE 2.368 #4 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 DeepSD MAPE 0.614 #4 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 DeepSD MSE 17.2723 #4 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 VDSR MAE 2.213 #5 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 VDSR MAPE 0.467 #5 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 VDSR MSE 17.2972 #5 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 SRResNet MAE 2.457 #6 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 SRResNet MAPE 0.713 #6 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 SRResNet MSE 17.3388 #6 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 ESPCN MAE 2.497 #7 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 ESPCN MAPE 0.732 #7 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 ESPCN MSE 17.6904 #7 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 SRCNN MAE 2.491 #8 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 SRCNN MAPE 0.714 #8 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 SRCNN MSE 18.4642 #8 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 HA MAE 2.251 #9 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 HA MAPE 0.336 #9 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P1 HA MSE 22.4770 #9 of 9 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P2 UrbanFM MAE 2.224 #2 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P2 UrbanFM MAPE 0.313 #2 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P2 UrbanFM MSE 18.7402 #2 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P2 UrbanFM-ne MAE 2.258 #3 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P2 UrbanFM-ne MAPE 0.320 #3 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P2 UrbanFM-ne MSE 19.2369 #3 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P3 UrbanFM MAE 2.318 #2 of 2 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P3 UrbanFM MAPE 0.315 #2 of 2 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P3 UrbanFM MSE 20.2140 #2 of 2 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P4 UrbanFM MAE 1.815 #2 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P4 UrbanFM MAPE 0.308 #2 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P4 UrbanFM MSE 12.2570 #2 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P4 UrbanFM-ne MAE 1.845 #3 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P4 UrbanFM-ne MAPE 0.309 #3 of 3 Archive leaderboard report
Fine-Grained Urban Flow Inference TaxiBJ-P4 UrbanFM-ne MSE 12.666 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections