REVIEW 8 cited by
Density-aware NeRF Ensembles: Quantifying Predictive Uncertainty in Neural Radiance Fields
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We show that ensembling effectively quantifies model uncertainty in Neural Radiance Fields (NeRFs) if a density-aware epistemic uncertainty term is considered. The naive ensembles investigated in prior work simply average rendered RGB images to quantify the model uncertainty caused by conflicting explanations of the observed scene. In contrast, we additionally consider the termination probabilities along individual rays to identify epistemic model uncertainty due to a lack of knowledge about the parts of a scene unobserved during training. We achieve new state-of-the-art performance across established uncertainty quantification benchmarks for NeRFs, outperforming methods that require complex changes to the NeRF architecture and training regime. We furthermore demonstrate that NeRF uncertainty can be utilised for next-best view selection and model refinement.
Forward citations
Cited by 8 Pith papers
-
GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction
GO-PRE proposes a next-best-view selection score that minimizes an upper bound on predictive rendering entropy over a user-specified target view manifold for 3D Gaussian Splatting.
-
TACO: Temporal Consensus Optimization for Continual Neural Mapping
TACO reformulates neural implicit mapping as temporal consensus optimization to enable continual adaptation to scene changes without data replay or storage.
-
Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction
Endo-NeRF++ augments EndoNeRF with multi-resolution hash grids, temporal feature blending, and Monte Carlo dropout uncertainty sampling, reporting up to 1.22 dB PSNR, 5.3% SSIM, and 55.1% LPIPS gains over the EndoNeRF...
-
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.
-
Predicting 3D structure by latent posterior sampling
A latent-variable approach uses diffusion models on NeRF-encoded scene representations to perform posterior sampling for 3D reconstruction from single-view, multi-view, noisy, sparse-pixel, or sparse-depth inputs.
-
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.
-
TACO: Temporal Consensus Optimization for Continual Neural Mapping
TACO is a replay-free continual neural-mapping method using importance-weighted consensus with past model snapshots to preserve stable geometry while revising outdated regions — validated quantitatively on static scen...
-
Endo-NeRF++: Uncertainty-Aware Neural Rendering with Multi-Resolution Hash Encoding for Dynamic Surgical Scene Reconstruction
Adding multi-resolution hash encoding, temporal blending, and MC-dropout-guided adaptive sampling to EndoNeRF yields small photometric gains on 2 proprietary and 2 StereoMIS surgical sequences.
Discussion (0). Sign in to comment.