A differentiable framework learns view-dependent 2D kernels from 3D ellipsoid primitives and latent vectors via projection and decoder networks for improved novel view synthesis.
3D Gaussian Splatting as a New Era: A Survey,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Proposes a reliability-aware frequency modeling framework using geometry-guided detail-demand prior and frequency-aware reliability map to guide high-frequency detail injection in low-resolution 3DGS, with a unified optimization scheme that improves fidelity on benchmarks.
A heterogeneous graph attention Q-network is introduced for AISC deployment that reduces completion time while improving load balance and energy use in dynamic UMEC networks.
citing papers explorer
-
Learning View-Dependent Splatting Kernels
A differentiable framework learns view-dependent 2D kernels from 3D ellipsoid primitives and latent vectors via projection and decoder networks for improved novel view synthesis.