Get the latest tech news
InstantSplat: Sparse-View SfM-Free Gaussian Splatting in Seconds
InstantSplat, unifies dense stereo priors with 3D-GS to build 3D Gaussians of large-scale scenes from sparse-view and pose-free images in less than 1 minute.
While novel view synthesis (NVS) from a sparse set of images has made substantial progress in 3D computer vision, it requires an accurate initial estimation of camera parameters using Structure-from-Motion (SfM). Moreover, the recent point-based representation (3D Gaussian Splatting or 3D-GS) is substantially dependent on the precision of SfM outcomes, leading to significant accumulated errors and limited generalization capability across varied datasets. Nonetheless, the non-uniform distribution of initial points from all pixels results in an excessive number of Gaussians, ielding a sub-optimal scene representation that compromises rendering speed and quality.
Or read this on Hacker News
