WideRange4D Multi-view Scene Dataset

WideRange4D is a new benchmark dataset jointly proposed by Peking University, University of Chinese Academy of Sciences and National University of Singapore in 2025.WideRange4D: Enabling High-Quality 4D Reconstruction with Wide-Range Movements and Scenes".

This dataset fills the gap in existing 4D reconstruction datasets in complex dynamic scenes by introducing 4D scene data with a large range of spatial motion. It excels in scene richness, motion complexity, and environmental diversity. It includes real-world scenes (such as urban streets and rural roads) and virtual scenes, covering short-distance, medium-distance, and long-distance motion, as well as complex motion trajectories, while also simulating a variety of weather conditions such as sunny days, rainy days, and sandstorms. The dataset was constructed in a very sophisticated process. It obtains diverse human, animal, and character models from platforms such as Mixamo and Unreal Engine's MetaHuman, and uses the skeletal system to control the generation of complex motion trajectories. It also uses Unreal Engine's FAB library to build modular scenes, and introduces dynamic weather changes through the Ultra Dynamic Sky plug-in. Finally, the configured CineCamera Actors capture RGB sequences from different angles at a frequency of 60 frames per second to ensure geometric and photometric consistency under multiple perspectives.

The WideRange4D dataset has a wide range of application scenarios, especially in the fields of animation and virtual reality. It can provide high-quality dynamic scene templates for animation, greatly saving modeling and rendering time, and also provide a realistic dynamic environment for virtual reality applications. In addition, the dataset can also be used to evaluate the performance of 4D reconstruction methods, especially in large-scale motion scenes. In order to verify the effectiveness of the dataset, a new 4D reconstruction method Progress4D is proposed in the paper and benchmarked on the WideRange4D dataset. Experimental results show that the 4D reconstruction quality of Progress4D in large-scale motion scenes is better than the existing state-of-the-art methods, which further proves the potential and value of the WideRange4D dataset in promoting the development of 4D reconstruction technology.