Aung, Sithu Sagong, Min-Cheol Cho, Junghyun 2025-09-02T03:00:28Z 2025-09-02T03:00:28Z 2025-08-26 2025-02 2159-5399 https://pubs.kist.re.kr/handle/201004/153100 We address an advanced challenge of predicting pedestrian occupancy as an extension of multi-view pedestrian detection in urban traffic. To support this, we have created a new synthetic dataset called MVP-Occ, designed for dense pedestrian scenarios in large-scale scenes. Our dataset provides detailed representations of pedestrians using voxel structures, accompanied by rich semantic scene understanding labels, facilitating visual navigation and insights into pedestrian spatial information. Furthermore, we present a robust baseline model, termed OmniOcc, capable of predicting both the voxel occupancy state and panoptic labels for the entire scene from multi-view images. Through in-depth analysis, we identify and evaluate the key elements of our proposed model, highlighting their specific contributions and importance. English ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE Multi-View Pedestrian Occupancy Prediction with a Novel Synthetic Dataset Conference 10.1609/aaai.v39i2.32172 1 39th AAAI Conference on Artificial Intelligence, pp.1782 - 1790 39th AAAI Conference on Artificial Intelligence 1782 1790 US Philadelphia, PA 2025-02-25 THIRTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, AAAI-25, VOL 39 NO 2 001478149200060