Pith. sign in

REVIEW 8 cited by

FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information

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

arxiv 2311.17874 v2 pith:CF656AY2 submitted 2023-11-29 cs.CV

classification cs.CV
keywords fieldsinformationradianceuncertaintyactivemodelquantificationselection
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This study addresses the challenging problem of active view selection and uncertainty quantification within the domain of Radiance Fields. Neural Radiance Fields (NeRF) have greatly advanced image rendering and reconstruction, but the cost of acquiring images poses the need to select the most informative viewpoints efficiently. Existing approaches depend on modifying the model architecture or hypothetical perturbation field to indirectly approximate the model uncertainty. However, selecting views from indirect approximation does not guarantee optimal information gain for the model. By leveraging Fisher Information, we directly quantify observed information on the parameters of Radiance Fields and select candidate views by maximizing the Expected Information Gain(EIG). Our method achieves state-of-the-art results on multiple tasks, including view selection, active mapping, and uncertainty quantification, demonstrating its potential to advance the field of Radiance Fields.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping

    cs.CV 2026-06 unverdicted novelty 7.0 of 10

    GaussLite conditions 3D Gaussian Splatting seeding density, gradient flow, and scaling on task relevance masks derived from LLM-parsed natural language and open-vocabulary detection, yielding +2.72 dB ROI PSNR gains o...

  2. Information-Regularized Constrained Inversion for Stable Avatar Editing from Sparse Supervision

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    A conditioning-guided constrained inversion method restricts avatar edits to a low-dimensional part-specific subspace and uses an information matrix spectrum from pipeline linearization to predict and ensure stability...

  3. GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction

    cs.CV 2026-07 conditional novelty 6.0 of 10

    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.

  4. Learning What Matters: Adaptive Information-Theoretic Objectives for Robot Exploration

    cs.RO 2026-05 unverdicted novelty 6.0 of 10

    QOED selects identifiable parameter directions via Fisher matrix eigenspace analysis and modifies exploration objectives to approximate ideal information gain under bounded nuisance assumptions, yielding 21-35% perfor...

  5. An Efficient Beam Search Algorithm for Active Perception in Mobile Robotics

    cs.RO 2026-04 unverdicted novelty 6.0 of 10

    Node-wise beam search with expected gain and RRAG graph construction outperforms prior active perception methods by at least 20% on representative tasks.

  6. FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    FreeScale generates scalable high-quality training data for generalizable novel view synthesis by certainty-aware sampling from imperfect scene reconstructions, delivering 2.7 dB PSNR gains on out-of-distribution tests.

  7. Coverage Optimization for Camera View Selection

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    COVER is a new coverage metric that selects camera views by prioritizing insufficiently observed geometry, yielding better NeRF reconstructions than prior active selection methods.

  8. Hestia: Voxel-Face-Aware Hierarchical Next-Best-View Acquisition for Efficient 3D Reconstruction

    cs.RO 2025-08 conditional novelty 5.0 of 10

    Hestia improves generalizable next-best-view planning for 3D reconstruction via hierarchical action search, diverse data, close-greedy strategy, and face-aware voxel design, yielding higher coverage and lower Chamfer ...

Pith tools