Scholarlink

In this paper, we present Dense Trajectory Fields (DTF), a novel low-level holistic approach inspired by optical-flow and trajectory methods, focusing on both spatial and temporal aspects at once. DTF contains the dense and long-term trajectories of all pixels from a reference frame, over an entire sequence. We solve it with DTF-Net, a fast and lightweight neural network, comprising 3 main components: (1) a joint iterative refinement of image and motion features over residual layers, (2) token-based Reciprocal Attention clusters and, (3) a Refinement Network that builds patch-to-patch cost-volumes around salient centroid trajectories. We extend the recent Kubric dataset to provide dense ground-truth over all pixels, to train DTF-Net. Experiments show that optical-flow and trajectory methods exhibit either temporal or spatial inconsistencies. Conversely, DTF-Net provides a better compromise while keeping faster, giving a coherent motion over the entire sequence. Code is available at https://github.com/MTournadre/DTFNet.git .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Dense Trajectory Fields: Consistent and Efficient Spatio-Temporal Pixel Tracking

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Marc Tournadre,
  • Catherine Soladié,
  • Nicolas Stoiber,
  • Pierre-Yves Richard

摘要

In this paper, we present Dense Trajectory Fields (DTF), a novel low-level holistic approach inspired by optical-flow and trajectory methods, focusing on both spatial and temporal aspects at once. DTF contains the dense and long-term trajectories of all pixels from a reference frame, over an entire sequence. We solve it with DTF-Net, a fast and lightweight neural network, comprising 3 main components: (1) a joint iterative refinement of image and motion features over residual layers, (2) token-based Reciprocal Attention clusters and, (3) a Refinement Network that builds patch-to-patch cost-volumes around salient centroid trajectories. We extend the recent Kubric dataset to provide dense ground-truth over all pixels, to train DTF-Net. Experiments show that optical-flow and trajectory methods exhibit either temporal or spatial inconsistencies. Conversely, DTF-Net provides a better compromise while keeping faster, giving a coherent motion over the entire sequence. Code is available at https://github.com/MTournadre/DTFNet.git .