A hybrid Gaussian-hash-grid representation with latent features and hard opacity falloffs reconstructs scenes more accurately than prior Gaussian splatting methods while using an order of magnitude fewer primitives.
IEEE Transactions on Visualization and Computer Graphics8(3), 223–238 (2002) 4 18 N
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hybrid Latents: Geometry-Appearance-Aware Surfel Splatting
A hybrid Gaussian-hash-grid representation with latent features and hard opacity falloffs reconstructs scenes more accurately than prior Gaussian splatting methods while using an order of magnitude fewer primitives.