GPU fluorescence microscopy deconvolution

Restore sharp, quantitative 3D microscopy in your browser.

FIREBAL runs Richardson–Lucy deconvolution on the GPU to reverse optical blur in confocal, widefield and light-sheet stacks — no CUDA setup, no desktop install. Upload a stack, generate or supply a PSF, and get a restored volume back.

No account needed to try — sign in to unlock larger stacks and saved jobs.
What it is

Deconvolution without the pipeline

Traditional deconvolution means wrangling a local CUDA toolchain, matching driver versions, and hand-tuning tiling to fit your GPU. FIREBAL moves all of that behind a web UI backed by serverless GPU workers.

🔬

Richardson–Lucy core

An iterative RL deconvolution engine written in CUDA C++, with regularisation and Wiener/OTF controls exposed per job.

Built-in PSF generation

Synthesise widefield, confocal and light-sheet point-spread functions from optical parameters — or upload your own measured PSF.

Auto-tiled for any GPU

Large volumes are split into VRAM-sized tiles automatically, with overlap blending so you never see seams in the result.

🧊

Full TZCYX stacks

Multi-channel, multi-timepoint stacks are handled natively and returned as ImageJ-compatible TIFFs.

☁️

Serverless GPUs

Jobs run on on-demand GPU workers and scale to zero when idle — you get the compute without renting a machine.

🌐

Nothing to install

The entire workflow lives in the browser. Open the app, drop in a stack, and download the restored volume.

How it works

From raw stack to restored volume in four steps

Upload

Drag in a TIFF stack. Large files stream straight to object storage, bypassing upload size limits.

Configure

Set the axis order, pick or generate a PSF, and tune iterations and regularisation.

Deconvolve

A GPU worker tiles the volume, runs Richardson–Lucy, and reassembles the result.

Download

Pull back an ImageJ-ready TIFF — sharper, with the optical blur reversed.

Access

Try it free, or sign in for the full version

Explore the tool with no account. Log in when you need the full workspace.

Free

Open the app

No account required
  • Full deconvolution UI & PSF generation
  • Run on shared GPU workers
  • Up to 200 MB per stack
  • One job per day
Launch free version →
Full · signed in

The complete workspace

Free account
  • Everything in the free version
  • Larger stacks & higher iteration caps
  • No daily job limit
  • Persistent job queue & history
Log in →
Who's behind it

The team

FIREBAL is built by a small group working at the intersection of microscopy, GPU computing and scientific tooling.

FN

Farhad Niknam

Deconvolution & CUDA core

Designs and maintains the Richardson–Lucy engine and the GPU processing pipeline.

FL

Friedrich Loparev

Platform & infrastructure

Builds the web app, the serverless GPU deployment and the object-storage backend.

+

Collaborators

Microscopy & testing

Researchers contributing sample data, optical parameters and validation across imaging modalities.

Ready to sharpen your stacks?

Open the app and run your first deconvolution in the browser.