Skip to content
AI News HubLIVE
Original source2 min read

RaFL: An Empirical Study of Random Filter Losses for Image Reconstruction

Summary

This paper introduces Random Filter Loss (RaFL), which compares predictions and targets through filters with random weights, avoiding pretrained features and task-specific loss engineering. RaFL outperforms or matches pixel loss on 2D and 3D image reconstruction tasks with minimal computational overhead.

SourcearXiv Computer VisionAuthor: Ruibo Wang, Fengbei Liu, Aleksei Tiulpin, Mert R. Sabuncu, Heejong Kim
RaFL: An Empirical Study of Random Filter Losses for Image Reconstruction
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 13 Nov 2026]

Title:RaFL: An Empirical Study of Random Filter Losses for Image Reconstruction

View a PDF of the paper titled RaFL: An Empirical Study of Random Filter Losses for Image Reconstruction, by Ruibo Wang and 4 other authors

View PDF HTML (experimental)

Abstract:Pixel losses train image reconstruction networks toward a point statistic of the target distribution, often averaging away fine textures under uncertainty. Perceptual losses alleviate this issue using pretrained features, but those features are inherently domain-specific. We study a random filter loss (RaFL) that compares prediction and target through filters with random weights, avoiding both pretrained features and task-specific loss engineering. RaFL combines random convolutions, random Fourier features, and random wavelet filters, automatically balancing their contributions through gradient-norm matching, eliminating manual loss-weight tuning and grid search. We systematically investigate three design choices: filter family, weight resampling schedule, and weight initialization. Based on validation PSNR and stability across random seeds, we select the configuration that uses all three filter families, redraws filters every optimization step, and employs Gaussian initialization. We evaluate RaFL on three 2D and two 3D image reconstruction tasks. RaFL outperforms a pixel loss on three tasks and matches it on two, and demonstrates stable performance across random seeds on all five tasks. RaFL adds less than 2% to the backbone's forward FLOPs and no inference cost, requiring $182\times$ fewer loss FLOPs than a VGG19 perceptual loss. These findings suggest that RaFL is a simple, tuning-free, and domain-agnostic loss objective for 2D and 3D image reconstruction.

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG)

Cite as: arXiv:2611.17707 [cs.CV]

(or arXiv:2611.17707v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.17707

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Ruibo Wang [view email] [v1] Fri, 13 Nov 2026 03:35:57 UTC (9,051 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled RaFL: An Empirical Study of Random Filter Losses for Image Reconstruction, by Ruibo Wang and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs cs.LG

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • RaFL combines random convolutions, random Fourier features, and random wavelet filters, automatically balancing their contributions via gradient-norm matching without manual tuning.
  • Across five image reconstruction tasks, RaFL outperforms pixel loss on three and matches it on two, with stable performance across random seeds.
  • RaFL adds less than 2% to forward FLOPs, incurs no inference cost, and requires 182× fewer loss FLOPs than a VGG19 perceptual loss.
  • The study systematically examines filter family, weight resampling schedule, and weight initialization, selecting a configuration with all three filter families, per-step redrawing, and Gaussian initialization.

Highlights and analysis are generated automatically and may contain errors. Check the original source.