Search papers, labs, and topics across Lattice.
This paper identifies and analyzes feature bias introduced by alpha-blending optimization in 3D Gaussian Splatting (3DGS) for visual localization. To mitigate this bias, they propose ULF-Loc, a framework that replaces biased feature optimization with geometry-weighted feature fusion and incorporates keypoint-consensus landmark sampling and local geometric consistency verification. Experiments on the Cambridge Landmarks dataset demonstrate a 17% reduction in mean median translation error compared to state-of-the-art methods, alongside significant improvements in training time and memory usage.
Alpha-blending, a core optimization in 3D Gaussian Splatting, subtly hobbles feature learning, but a geometry-weighted fusion approach can unlock more accurate and efficient visual localization.
Visual localization is a core technology for augmented reality and autonomous navigation. Recent methods combine the efficient rendering of 3D Gaussian Splatting (3DGS) with feature-based localization. These methods rely on direct matching between 2D query features and the 3D Gaussian feature field, but this often results in mismatches due to an inherent bias in the learned Gaussian feature. We theoretically analyze the feature learning process in 3DGS, revealing that the widely adopted $\alpha$-blending optimization inherently introduces bias into 3D point features. This bias stems from the entanglement between individual Gaussians and their neighboring Gaussians, making the learned features unsuitable for precise matching tasks. Motivated by these findings, we propose ULF-Loc, an unbiased landmark feature framework that replaces biased feature optimization with geometry-weighted feature fusion. We further introduce keypoint-consensus landmark sampling to select reliable Gaussians and local geometric consistency verification to reject mismatches caused by rendering artifacts. On the Cambridge Landmarks dataset, ULF-Loc reduces the mean median translation error by 17\% compared to the state-of-the-art, while achieving superior efficiency with only 1/10 the training time and 1/6 the GPU memory of STDLoc.
