{"ID":2887488,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01170","arxiv_id":"2508.01170","title":"DELTAv2: Accelerating Dense 3D Tracking","abstract":"We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking becomes expensive when handling a large number of trajectories. To address this, we introduce a coarse-to-fine strategy that begins tracking with a small subset of points and progressively expands the set of tracked trajectories. The newly added trajectories are initialized using a learnable interpolation module, which is trained end-to-end alongside the tracking network. Second, we propose an optimization that significantly reduces the cost of correlation feature computation, another key bottleneck in prior methods. Together, these improvements lead to a 5-100x speedup over existing approaches while maintaining state-of-the-art tracking accuracy.","short_abstract":"We propose a novel algorithm for accelerating dense long-term 3D point tracking in videos. Through analysis of existing state-of-the-art methods, we identify two major computational bottlenecks. First, transformer-based iterative tracking becomes expensive when handling a large number of trajectories. To address this,...","url_abs":"https://arxiv.org/abs/2508.01170","url_pdf":"https://arxiv.org/pdf/2508.01170v2","authors":"[\"Tuan Duc Ngo\",\"Ashkan Mirzaei\",\"Guocheng Qian\",\"Hanwen Liang\",\"Chuang Gan\",\"Evangelos Kalogerakis\",\"Peter Wonka\",\"Chaoyang Wang\"]","published":"2025-08-02T03:15:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}