Published March 21, 2024 | Version 1.0
Dataset Open

Deblur-NeRF-SAI

Description

Modified version of the Deblur-NeRF dataset, used in under the CC BY 4.0 license. The original dataset, created by  Ma Li, Li Xiaoyu, Liao Jing, Zhang Qi, Wang Xuan, Wang Jue, and Pedro V. Sander , is described in https://doi.org/10.1109/CVPR52688.2022.01252 and avaiable at https://limacv.github.io/deblurnerf/.

The data was extended to include a variant with artificial rolling shutter artefacts. In addition, we regenerated the motion blurred images using the Blender files, which we modified by fixing the random seed, and also included velocity information in our outputs. Furthermore, we switched from the custom 10-sample blur implementation to Blender's built-in motion blur and rolling-shutter effects, which are less prone to sampling artefacts. Finally, we adjusted the caustics rendering settings in the Blender scenes to reduce non-deterministic raytracing sampling noise in the data with reasonable sample counts.

 

Files

blend_files.zip

Files (958.5 MB)

Name Size Download all
md5:204a69ac2a39550927fc797b57d5e9ab
472.4 MB Preview Download
md5:36793b2768d69a8788219e087329e024
274.2 MB Preview Download
md5:f9222baf6534f8dac95651aed354bb7f
211.9 MB Preview Download

Additional details

Related works

Is derived from
Publication: 10.1109/CVPR52688.2022.01252 (DOI)
Is described by
Preprint: arXiv:2403.13327 (arXiv)