ActiveInitSplat: How Active Image Selection Helps Gaussian Splatting
This addresses the challenge of image selection for GS initialization, which is crucial for rendering quality, but is incremental as it builds on existing GS methods.
The paper tackles the problem of selecting training images for Gaussian splatting (GS) to improve rendering performance, proposing ActiveInitSplat, which actively chooses images based on 3D scene criteria, resulting in significant improvements in LPIPS, SSIM, and PSNR metrics over passive baselines.
Gaussian splatting (GS) along with its extensions and variants provides outstanding performance in real-time scene rendering while meeting reduced storage demands and computational efficiency. While the selection of 2D images capturing the scene of interest is crucial for the proper initialization and training of GS, hence markedly affecting the rendering performance, prior works rely on passively and typically densely selected 2D images. In contrast, this paper proposes `ActiveInitSplat', a novel framework for active selection of training images for proper initialization and training of GS. ActiveInitSplat relies on density and occupancy criteria of the resultant 3D scene representation from the selected 2D images, to ensure that the latter are captured from diverse viewpoints leading to better scene coverage and that the initialized Gaussian functions are well aligned with the actual 3D structure. Numerical tests on well-known simulated and real environments demonstrate the merits of ActiveInitSplat resulting in significant GS rendering performance improvement over passive GS baselines, in the widely adopted LPIPS, SSIM, and PSNR metrics.