Running summarizing tools on a new article

Abstract: Various Radiance Field methods have been recently explored for photo-realistic novel-view synthesis of scenes captured with multiple views given a set of images. However, none of them has provided the high visual quality with the real-time rendering of 3D Gaussian Splatting (3D-GS) without a trade-off in neither the speed nor the quality. On the other hand, the astonishing improvements of 3D Gaussian Splatting come at the cost of having a huge storage footprint due to the massive number of gaussians per model. In this paper, we focus on further optimizing the creation of gaussians throughout the training iterations to control the number of gaussians needed to represent the model. We propose three modifications blocks to the original Gaussian Splatting method that allow the state-of-the-art visual quality with lower number of gaussians while maintaining the same training time and real-time rendering of the original Gaussian Splatting method. By means of diverse simulations, our modifications effectively minimize the number of gaussians with a slightly improved visual quality or a negligible loss in the visual quality according to which of the proposed blocks are applied.