New technique sharpens images from single-lens cameras, cutting artifacts in half
Researchers have combined artificial intelligence with specialized camera technology to dramatically improve image quality from compact plenoptic cameras. The advance could enable sharper 3D imaging on smartphones and autonomous vehicles without bulky multi-camera setups, reducing both hardware costs and processing complexity.
Originaltitel: 3D-Gaussian Splatting Representation of Rendered Views from Plenoptic 2.0 Lenslet Images
<p>Thanks to plenoptic cameras, rich information on the radiance of a scene can be conveniently captured without heavy devices like camera arrays. However, rendering techniques are needed to generate views for human visual perception. Existing patch extraction-based rendering techniques can generate views from the lenslet images captured by plenoptic cameras, but they suffer from the inherent problem of artifacts and the limited views to be rendered. In this paper, we present a new view rendering technique from plenoptic 2.0 camera-captured lenslet image by using 3-dimensional gaussian splatting (3DGS). At its first step, the reference lenslet converter (RLC) provided by MPEG LVC AhG, one of the existing patch extraction methods, generates initial views with the help of estimated disparity between adjacent micro images in the lenslet image. At its second step, the 3DGS generates the final views after being trained by the initial views. The rendering results obtained by the proposed 2-step approach show significantly fewer artifacts in the rendered views than the patch stitching process of the existing method.</p>