An empirical 3DGS variant that trains from random point initialization with edge-weighted, opacity-weighted, and channel-weighted loss terms, reporting large gains on Mip-NeRF 360 and LLFF.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
AttentionGS: Towards Initialization-Free 3D Gaussian Splatting via Structural Attention
An empirical 3DGS variant that trains from random point initialization with edge-weighted, opacity-weighted, and channel-weighted loss terms, reporting large gains on Mip-NeRF 360 and LLFF.