TROPHIES：从多视角视频中时序重建场所、人体与相机
TROPHIES: Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos
把动态人体、静态场景与相机位姿放进同一全局坐标系联合优化，并用尺度一致性、接触先验与跨视角时序一致性做耦合，可直接借鉴到多视角/自我中心视频下的 4D 场景重建与人体-场景交互建模。
原文依据 jointly estimate dynamic humans, static scenes, and camera poses in one global coordinate frame
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在全局一致的 4D 空间中重建人体及其周围环境，是实现全面感知的关键。然而，已有工作通常假设单视角输入，或将人体、场景与相机解耦处理，因而无法恢复连贯的几何、稳定的运动以及物理对齐的轨迹。这些局限促使我们提出一项新任务：从多视角视频进行人体-场景-相机的统一重建，其目标是在同一个全局坐标系中联合估计动态人体、静态场景与相机位姿。我们提出 TROPHIES——从多视角视频中时序重建场所、人体与相机——一个为该任务量身定制的统一框架。TROPHIES 包含一个人体分支，通过时序与空间推理对人体建模；以及一个场景分支，借助人体感知注意力重建静态几何。一个全局对齐与优化模块通过施加尺度一致性、接触先验与跨视角时序一致性来耦合这两个分支。在 EgoHuman 与 EgoExo4D 上的实验表明，TROPHIES 能够实现全局对齐、物理合理的 4D 重建，并在全局保真度与人体-场景一致性两方面持续优于现有范式。
英文原文摘要 1259 字符
Reconstructing humans and their surrounding environments in a globally consistent 4D space is essential for comprehensive perception. However, prior works typically assume single-view inputs or decouple humans, scenes, and cameras, making them unable to recover coherent geometry, stable motion, and physically aligned trajectories. These limitations motivate us to introduce a new task: unified human-scene-camera reconstruction from multi-view videos, which aims to jointly estimate dynamic humans, static scenes, and camera poses in one global coordinate frame. We propose TROPHIES--Temporal Reconstruction of Places, Humans, and Cameras from Multi-view Videos--a unified framework tailored for this task. TROPHIES features a Human Branch that models human through temporal and spatial reasoning, and a Scene Branch that reconstructs static geometry with human-aware attention. A global alignment and optimization module couples both branches by enforcing scale consistency, contact priors, and cross-view temporal coherence. Experiments on EgoHuman and EgoExo4D demonstrate that TROPHIES achieves globally aligned, physically plausible 4D reconstructions and consistently outperforms existing paradigms in both global fidelity and human-scene consistency.