A two-stage method trains NeRF latents then a diffusion prior to sample posteriors for 3D reconstruction from varied observations including single-view, multi-view, noisy, sparse pixels, and sparse depth.
Given an input image of a scene, each model generates multiple novel views, which are then used to train a TensoRF (NeRF) model
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 method trains NeRF latents then a diffusion prior to sample posteriors for 3D reconstruction from varied observations including single-view, multi-view, noisy, sparse pixels, and sparse depth.