[论文] Syn4D: A Multiview Synthetic 4D Dataset

论文概要

研究领域: CV 作者: Zeren Jiang, Yushi Lan, Yihang Luo, Yufan Deng, Zihang Lai, Edgar Sucar, Christian Rupprecht, Iro Laina, Diane Larlus, Chuanxia Zheng, Andrea Vedaldi 发布时间: 2026-05-06 arXiv: 2605.05207

中文摘要

从单目视频进行密集3D重建和动态场景跟踪仍然是计算机视觉中一个重要的开放挑战。该领域的进展受到高质量数据集稀缺的制约，这些数据集需要具有密集、完整且准确的几何标注。为解决这一限制，我们引入了Syn4D——一个多视图合成动态场景数据集，包含真实的相机运动、深度图、密集跟踪和参数化人体姿态标注。Syn4D的关键特性是能够将任意像素反投影到3D空间中的任意时间和任意相机视角。我们在多个下游任务上进行了广泛评估，以证明所提出数据集的实用性和有效性，包括4D场景重建、3D点跟踪、几何感知相机重定向和人体姿态估计。实验结果凸显了Syn4D在促进动态场景理解和时空建模研究方面的潜力。

原文摘要

Dense 3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision. Progress in this area has been constrained by the scarcity of high-quality datasets with dense, complete, and accurate geometric annotations. To address this limitation, we introduce Syn4D, a multiview synthetic dataset of dynamic scenes that includes ground-truth camera motion, depth maps, dense tracking, and parametric human pose annotations. A key feature of Syn4D is the ability to unproject any pixel into 3D to any time and to any camera. We conduct extensive evaluations across multiple downstream tasks to demonstrate the utility and effectiveness of the proposed dataset, including 4D scene reconstruction, 3D point tracking, geometry-aware camera retargeting, and human pose estimation. The experimental results highlight Syn4D's potential to facilitate research in dynamic scene understanding and spatiotemporal modeling.

自动采集于 2026-05-08

#论文 #arXiv #CV #小凯