V-DPM：基于动态点图的四维视频重建
V-DPM: 4D Video Reconstruction with Dynamic Point Maps
把 DUSt3R 的不变点图扩展到视频序列并显式建模每点三维运动，可直接复用于动态场景的前馈式 4D 重建与相机位姿估计；其「在 VGGT 上用少量合成数据适配新表示」的做法，也为把静态预训练重建器迁移到动态设定提供了可复用范式。
原文依据 a modest amount of synthetic data suffices to adapt it into an effective V-DPM predictor
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论诸如 DUSt3R 的不变点图这类强大的三维表示能够编码三维形状与相机参数，已显著推动了前馈式三维重建的发展。点图假设场景是静态的，而动态点图（DPM）通过同时表示场景运动，将该概念扩展到动态三维内容。然而，DPM 迄今仅限于图像对，并且与 DUSt3R 一样，在涉及多于两个视角时需要经过优化进行后处理。我们认为 DPM 应用于视频时更为有用，并据此提出 V-DPM 加以验证。首先，我们展示了如何为视频构建 DPM，以优化其表示能力、便于神经网络预测，并支持复用预训练模型。其次，我们在近期强大的三维重建器 VGGT 之上实现了这些想法。尽管 VGGT 是在静态场景上训练的，我们表明仅需少量合成数据即可将其适配为有效的 V-DPM 预测器。由此在动态场景下取得了最优的三维与四维重建效果。特别地，与 P3 等近期对 VGGT 的动态扩展不同，DPM 不仅恢复动态深度，还恢复场景中每个点的三维运动。
英文原文摘要 1176 字符
Powerful 3D representations such as DUSt3R's invariant point maps, which encode 3D shape and camera parameters, have significantly advanced feed-forward 3D reconstruction. While point maps assume static scenes, Dynamic Point Maps (DPMs) extend the concept to dynamic 3D content by also representing scene motion. However, DPMs have so far been limited to image pairs and, like DUSt3R, require post-processing via optimisation when more than two views are involved. We argue that DPMs are more useful when applied to videos and introduce V-DPM to demonstrate this. First, we show how to set up DPMs for videos to optimise representational power, facilitate neural prediction, and enable reuse of pretrained models. Second, we implement these ideas on top of VGGT, a recent powerful 3D reconstructor. Although VGGT was trained on static scenes, we show that a modest amount of synthetic data suffices to adapt it into an effective V-DPM predictor. This yields state-of-the-art 3D and 4D reconstruction in dynamic settings. In particular, unlike recent dynamic extensions of VGGT such as P3, DPMs recover not only dynamic depth but also the 3D motion of every point in the scene.