Exploration Matters for Escaping the Blur Trap in 3D Gaussian Splatting

Key points

The core argument is that blur in 3DGS comes not from insufficient data or model capacity, but from bias in the optimization dynamics themselves.
Theoretically, it proves that 3D position updates derived from 2D gradients are orthogonal to the camera-to-Gaussian viewing ray, and reports that the 2D position component dominates the other two components by two to three orders of magnitude throughout training.
It splits blur into two kinds: far-side blur caused by missing depth signals and near-side blur caused by alpha blending suppressing the signal to increase density.
The remedy is simple: periodically seed candidate Gaussians at random positions, prune bad candidates by opacity pruning, and randomly split some Gaussians regardless of accumulated gradients.
Across five datasets, Mip-NeRF 360, Tanks and Temples, Deep Blending, OMMO, and DL3DV, and in the 4DGS extension, image quality improves, with PSNR on Tanks and Temples rising from 23.73 to 24.37 and DL3DV from 27.16 to 28.43.
Ablation studies show that forcing more splits by lowering the density threshold only inflates the number of points without materially improving quality, confirming that the gain comes from exploration itself rather than from simply increasing the count.

External research summaries. These are not HDATF publications or measured product results.