RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Guangcong, Li, Teng, Zhou, Xianpan, Li, Xi
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916685581123584
author Zheng, Guangcong
Li, Teng
Zhou, Xianpan
Li, Xi
author_facet Zheng, Guangcong
Li, Teng
Zhou, Xianpan
Li, Xi
contents Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K. While these datasets enable basic viewpoint control, they fail to capture dynamic scene interactions and lack metric-scale geometric consistency-critical for synthesizing realistic object motions and precise camera trajectories in complex environments. To bridge this gap, we introduce the first fully open-source, high-resolution dynamic-scene dataset with metric-scale camera annotations in https://github.com/ZGCTroy/RealCam-Vid.
format Preprint
id arxiv_https___arxiv_org_abs_2504_08212
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements
Zheng, Guangcong
Li, Teng
Zhou, Xianpan
Li, Xi
Computer Vision and Pattern Recognition
Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K. While these datasets enable basic viewpoint control, they fail to capture dynamic scene interactions and lack metric-scale geometric consistency-critical for synthesizing realistic object motions and precise camera trajectories in complex environments. To bridge this gap, we introduce the first fully open-source, high-resolution dynamic-scene dataset with metric-scale camera annotations in https://github.com/ZGCTroy/RealCam-Vid.
title RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.08212