paper-with-me

홈 › Papers

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

2025-04-11 · Guangcong Zheng, Teng Li, Xianpan Zhou, Xi Li

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.

📄 PDF Abstract BibTeX arXiv:2504.08212

Code (1)

zgctroy/realcam-vid 공식 구현 pytorch

Tasks

Video Generation

Similar Papers 제목 키워드 기반

RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control

2025-02-14 · Teng Li, Guangcong Zheng, Rui Jiang, Shuigenzhan 외

Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches. However, they also introduce significant u…

3D Scene ReconstructionDepth EstimationImage to Video GenerationVideo Generation

RealCam: Real-Time Novel-View Video Generation with Interactive Camera Control

2026-05-07 · Youcan Xu, Jiaxin Shi, Zhen Wang, Wensong Song 외 arxiv

Camera-controlled video-to-video (V2V) generation enables dynamic viewpoint synthesis from monocular footage, holding immense potential for interactive filmmaking and live broadcasting. However, existing implicit synthes…

Data AugmentationVideo Generation

An End-to-End Real-World Camera Imaging Pipeline

2024-11-16 · Kepeng Xu, Zijia Ma, Li Xu, Gang He 외

Recent advances in neural camera imaging pipelines have demonstrated notable progress. Nevertheless, the real-world imaging pipeline still faces challenges including the lack of joint optimization in system components, c…

Image CompressionTone Mapping

RealCamo: Boosting Real Camouflage Synthesis with Layout Controls and Textual-Visual Guidance

2025-12-28 · Chunyuan Chen, Yunuo Cai, Shujuan Li, Weiyun Liang 외 arxiv

Camouflaged image generation (CIG) has recently emerged as an efficient alternative for acquiring high-quality training data for camouflaged object detection (COD). However, existing CIG methods still suffer from a subst…

Object DetectionImage Generation

Super-Resolution Appearance Transfer for 4D Human Performances

2021-08-31 · Marco Pesavento, Marco Volino, Adrian Hilton

A common problem in the 4D reconstruction of people from multi-view video is the quality of the captured dynamic texture appearance which depends on both the camera resolution and capture volume. Typically the requiremen…

4D reconstruction4k8kAppearance Transfer+1