Pith. sign in

REVIEW 3 cited by

Preconditioners for the Stochastic Training of Neural Fields

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2402.08784 v2 pith:4ZY34OIT submitted 2024-02-13 cs.CV cs.LG

Shin-Fang Chng , Hemanth Saratchandran , Simon Lucey This is my paper · ORCID
classification cs.CVcs.LG
keywords neuralfieldstrainingstochasticoptimizationpreconditionersaccelerateaccuracy
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Neural fields encode continuous multidimensional signals as neural networks, enabling diverse applications in computer vision, robotics, and geometry. While Adam is effective for stochastic optimization, it often requires long training times. To address this, we explore alternative optimization techniques to accelerate training without sacrificing accuracy. Traditional second-order methods like L-BFGS are unsuitable for stochastic settings. We propose a theoretical framework for training neural fields with curvature-aware diagonal preconditioners, demonstrating their effectiveness across tasks such as image reconstruction, shape modeling, and Neural Radiance Fields (NeRF).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

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

  1. TetraSDF: Analytic Isosurface Extraction with Multi-resolution Tetrahedral Grid

    cs.CV 2025-11 conditional novelty 7.0 of 10

    TetraSDF extracts triangle meshes that match a neural SDF's zero-level set to near machine precision by replacing trilinear grid interpolation with barycentric tetrahedral interpolation, keeping the entire network pie...

  2. Enhancing Implicit Neural Representations via Symmetric Power Transformation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A reversible symmetric power transformation improves implicit neural representation fitting across audio, image, and video tasks with no added storage cost.

  3. DR-BFR: Degradation Representation with Diffusion Models for Blind Face Restoration

    cs.CV 2024-11 conditional novelty 5.0 of 10

    DR-BFR learns a content-free degradation representation from low-quality faces and uses it as a prompt to condition a latent diffusion face restoration model, improving FID and NIQE on face benchmarks.

Pith tools