{"ID":2890671,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.19691","arxiv_id":"2507.19691","title":"Co-Win: Joint Object Detection and Instance Segmentation in LiDAR Point Clouds via Collaborative Window Processing","abstract":"Accurate perception and scene understanding in complex urban environments is a critical challenge for ensuring safe and efficient autonomous navigation. In this paper, we present Co-Win, a novel bird's eye view (BEV) perception framework that integrates point cloud encoding with efficient parallel window-based feature extraction to address the multi-modality inherent in environmental understanding. Our method employs a hierarchical architecture comprising a specialized encoder, a window-based backbone, and a query-based decoder head to effectively capture diverse spatial features and object relationships. Unlike prior approaches that treat perception as a simple regression task, our framework incorporates a variational approach with mask-based instance segmentation, enabling fine-grained scene decomposition and understanding. The Co-Win architecture processes point cloud data through progressive feature extraction stages, ensuring that predicted masks are both data-consistent and contextually relevant. Furthermore, our method produces interpretable and diverse instance predictions, enabling enhanced downstream decision-making and planning in autonomous driving systems.","short_abstract":"Accurate perception and scene understanding in complex urban environments is a critical challenge for ensuring safe and efficient autonomous navigation. In this paper, we present Co-Win, a novel bird's eye view (BEV) perception framework that integrates point cloud encoding with efficient parallel window-based feature...","url_abs":"https://arxiv.org/abs/2507.19691","url_pdf":"https://arxiv.org/pdf/2507.19691v1","authors":"[\"Haichuan Li\",\"Tomi Westerlund\"]","published":"2025-07-25T22:14:23Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[]","has_code":false}