Get the latest tech news
Deblur-GS: 3D Gaussian splatting from camera motion blurred images
3D Gaussian Splatting from Camera Motion Blurred Images
The introduction of 3D Gaussian splatting (3DGS) has successfully addressed the issues of prolonged training times and slow rendering speeds associated with the Neural Radiance Field (NeRF), all while preserving the quality of reconstructions. In this paper, we propose the Deblur-GS method for reconstructing 3D Gaussian points to create a sharp radiance field from a camera motion blurred image set. Deblur-GS consistently achieves superior performance and rendering quality when compared to previous methods, as demonstrated in evaluations conducted on both synthetic and real datasets.
Or read this on Hacker News
