Voxel51/Syn4D_RGBD
收藏资源简介:
Syn4D RGBD是一个大规模、全合成的多视图动态场景数据集,旨在推动4D重建、深度估计、3D点跟踪、新视图合成和人体姿态估计等研究。它提供了密集、完整和准确的几何注释,包括每像素深度图、多视图相机轨迹、密集长程3D点跟踪以及参数化SMPL-X人体注释,涵盖使用Unreal Engine 5渲染的多样化室内和室外环境。这个FiftyOne数据集是完整Syn4D版本的一个精选子集,包含3个场景(共45个序列),每个序列有8个同步的多相机视频剪辑,配有每帧深度热图、实例分割掩码和相机姿态元数据,以及一个从所有8个视图重建的融合彩色3D点云。数据集由牛津大学视觉几何组、南洋理工大学和Naver Labs Europe等机构创建,许可证允许用于AI训练,语言为英语(字幕),相关论文为arXiv:2605.05207。
Syn4D RGBD is a large-scale, fully-synthetic multiview dataset of dynamic scenes designed to advance research in 4D reconstruction, depth estimation, 3D point tracking, novel-view synthesis, and human pose estimation. It provides dense, complete, and accurate geometric annotations — including per-pixel depth maps, multi-view camera trajectories, dense long-range 3D point tracks, and parametric SMPL-X human body annotations — across a diverse collection of indoor and outdoor environments rendered with Unreal Engine 5. This FiftyOne dataset is a curated subset of the full Syn4D release, covering 3 scenes (45 sequences total), with each sequence available as 8 synchronised multi-camera video clips, paired with per-frame depth heatmaps, instance segmentation masks, and camera pose metadata, and a fused coloured 3D point cloud reconstructed from all 8 views. The dataset is curated by Visual Geometry Group (VGG), University of Oxford; Nanyang Technological University; Naver Labs Europe, licensed for AI training use, with English captions, and the paper is arXiv:2605.05207.




