匹配每一对以跟踪每一个点：PairFormer 用于全对跟踪与视频轨迹场
Matching Every Pair to Track Every Point: PairFormer for All-Pairs Tracking and Video Trajectory Fields
PairFormer 将视频中所有帧对的密集对应关系一次性预测为全对轨迹场，这种全对跟踪的设定和 CorrBank 可学习相关银行的设计，为视频运动分析提供了新的可复用范式，可直接用于光流、点跟踪和视频编辑中的轨迹提取。
原文依据 We formulate All-Pairs Tracking (APT): given a video, predict dense displacement and visibility for every source-target frame pair
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论跟踪任意点（TAP）回答了查询条件对应问题，但将视频中稠密的全对结构留为隐式。我们形式化了全对跟踪（APT）：给定一个视频，预测每个源-目标帧对的稠密位移和可见性，从中可以读出逐像素轨迹。为此，我们提出了 PairFormer，一个前馈 Transformer，单次前向即可解决 APT。一个时空图像块编码器为所有帧计算时间条件特征。CorrBank 为每个帧对构建可学习的相关银行并产生成对运动令牌。一个广播运动混合器聚合轨迹级上下文并将其广播回去以细化成对运动令牌。一个轨迹检测头首先预测粗粒度的稠密位移、可见性和置信度，然后迭代细化它们以形成连贯的全对轨迹场。为了大规模支持 APT，我们开发了 PAIRender，一个数据平台，可合成具有稠密标注的照片级真实感动态场景。我们从 PAIRender 派生了一个训练集（π-R10K）和一个基准（APT-Bench），并带有全对全评估协议。实验表明，PairFormer 在 APT-Bench 上取得了强劲性能，并在标准 TAP 基准上取得了有竞争力的结果。代码和数据集将在发表后发布。
英文原文摘要 1335 字符
Tracking-any-point (TAP) answers query-conditioned correspondence but leaves the dense, all-pairs structure of a video implicit. We formulate All-Pairs Tracking (APT): given a video, predict dense displacement and visibility for every source-target frame pair, from which per-pixel trajectories can be read out. To this end, we propose PairFormer, a feed-forward transformer that addresses APT in a single pass. A spatio-temporal patch encoder computes temporally conditioned features for all frames. \revaddtwo CorrBank builds a learnable correlation bank for each frame pair and produces pairwise motion tokens. A broadcast motion mixer aggregates trajectory-wise context and broadcasts it back to refine the pairwise motion tokens. A trajectory head first predicts coarse dense displacement, visibility, and confidence, and then refines them iteratively to form a coherent all-pairs trajectory field. To support APT at scale, we develop PAIRender, a data platform that synthesizes photo-realistic dynamic scenes with dense annotations. From PAIRender we derive a training set (\pi-R10K) and a benchmark (APT-Bench) with an all-to-all evaluation protocol. Experiments show that PairFormer achieves strong performance on APT-Bench and competitive results on standard TAP benchmarks. Code and dataset will be released upon publication.