TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
This addresses the issue of camera parameter estimation for 3D Gaussian Splatting in complex scenarios, offering an incremental improvement over previous COLMAP-Free methods.
The paper tackles the problem of 3D Gaussian Splatting's dependence on accurate pre-computed camera parameters by introducing TrackGS, which uses global feature track constraints to optimize camera poses and intrinsics jointly, achieving state-of-the-art performance on challenging datasets with severe camera movements.
While 3D Gaussian Splatting (3DGS) has advanced ability on novel view synthesis, it still depends on accurate pre-computaed camera parameters, which are hard to obtain and prone to noise. Previous COLMAP-Free methods optimize camera poses using local constraints, but they often struggle in complex scenarios. To address this, we introduce TrackGS, which incorporates feature tracks to globally constrain multi-view geometry. We select the Gaussians associated with each track, which will be trained and rescaled to an infinitesimally small size to guarantee the spatial accuracy. We also propose minimizing both reprojection and backprojection errors for better geometric consistency. Moreover, by deriving the gradient of intrinsics, we unify camera parameter estimation with 3DGS training into a joint optimization framework, achieving SOTA performance on challenging datasets with severe camera movements.