A two-stage latent-variable model uses diffusion-based score matching to sample 3D scenes from posteriors conditioned on varied observations via volumetric rendering likelihoods.
Along each ray, we sample 220 3D points and project them onto the tri-planes of both the RGB and density planes separately
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
-
Predicting 3D structure by latent posterior sampling
A two-stage latent-variable model uses diffusion-based score matching to sample 3D scenes from posteriors conditioned on varied observations via volumetric rendering likelihoods.