Complet4R：几何完整的四维重建
Complet4R: Geometric Complete 4D Reconstruction
用 decoder-only Transformer 在整段视频上做全局注意力，把其他帧可见的遮挡区域直接累积到当前帧，从而在单次前向中同时完成动态场景重建与几何补全；这一「重建即补全」的范式可迁移到动态 NeRF/高斯泼溅的遮挡补全与长时序点跟踪。
原文依据 reconstructing a complete geometry for every single timestamp, including occluded regions visible in other frames
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 Complet4R，一个用于几何完整四维重建的新型端到端框架，旨在为动态场景恢复时序一致且几何完整的重建结果。该方法通过将完整上下文直接累积到每一帧上，把几何完整四维重建任务形式化为重建与补全的统一框架。与依赖成对重建或局部运动估计的已有方法不同，Complet4R 采用仅解码器 Transformer，直接从序列视频输入出发对全部上下文进行全局操作，为每个时间戳重建完整几何，包括在其他帧中可见的遮挡区域。在我们提出的几何完整四维重建基准以及三维点跟踪任务上，该方法均取得了最优性能。代码将开源以支持后续研究。
英文原文摘要 911 字符
We introduce Complet4R, a novel end-to-end framework for Geometric Complete 4D Reconstruction, which aims to recover temporally coherent and geometrically complete reconstruction for dynamic scenes. Our method formalizes the task of Geometric Complete 4D Reconstruction as a unified framework of reconstruction and completion, by directly accumulating full contexts onto each frame. Unlike previous approaches that rely on pairwise reconstruction or local motion estimation, Complet4R utilizes a decoder-only transformer to operate all context globally directly from sequential video input, reconstructing a complete geometry for every single timestamp, including occluded regions visible in other frames. Our method demonstrates the state-of-the-art performance on our proposed benchmark for Geometric Complete 4D Reconstruction and the 3D Point Tracking task. Code will be released to support future research.