Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience
This provides a new dataset for researchers in 3D reconstruction and VR/AR, addressing a specific gap in resources, though it is incremental as it builds upon existing capture methods.
The authors tackled the lack of large-space dense light field datasets by building a custom mobile multi-camera system that captures high-quality, dense images for 3D scene reconstruction, achieving an average density of 134.68 views per unit sphere and validating it on algorithms like NeRF and 3D Gaussian splitting.
We have built a custom mobile multi-camera large-space dense light field capture system, which provides a series of high-quality and sufficiently dense light field images for various scenarios. Our aim is to contribute to the development of popular 3D scene reconstruction algorithms such as IBRnet, NeRF, and 3D Gaussian splitting. More importantly, the collected dataset, which is much denser than existing datasets, may also inspire space-oriented light field reconstruction, which is potentially different from object-centric 3D reconstruction, for immersive VR/AR experiences. We utilized a total of 40 GoPro 10 cameras, capturing images of 5k resolution. The number of photos captured for each scene is no less than 1000, and the average density (view number within a unit sphere) is 134.68. It is also worth noting that our system is capable of efficiently capturing large outdoor scenes. Addressing the current lack of large-space and dense light field datasets, we made efforts to include elements such as sky, reflections, lights and shadows that are of interest to researchers in the field of 3D reconstruction during the data capture process. Finally, we validated the effectiveness of our provided dataset on three popular algorithms and also integrated the reconstructed 3DGS results into the Unity engine, demonstrating the potential of utilizing our datasets to enhance the realism of virtual reality (VR) and create feasible interactive spaces. The dataset is available at our project website.