IMG · Images tools

Unblur Image

Shareable link

Settings are written to the URL as you change them. Nothing differs from the defaults yet.

Recover a softly blurred photo by inverting the blur. A photo that missed focus, or moved during the exposure, is the sharp scene convolved with a small kernel: a disc for a missed focus, a short line for camera shake. Deconvolution solves for the scene given that kernel. On a blur of a few pixels the result is a genuinely sharper picture, with text readable again and edges back to a single line.

Choose the kernel

Blur type names the physical cause. Lens is a defocus: every point became a disc, and the slider sets its radius in source pixels. Motion is a smear along one direction: the slider sets its length and Angle sets the direction, 0 for horizontal shake and 90 for vertical. Soft is a Gaussian haze with no single cause, which fits a picture that was upscaled, denoised too hard, or scanned slightly out of focus.

The size is the setting that matters most, and the picture tells you when it is right. Too small and the result is only a little sharper. Too large and edges grow a halo, then a second ripple. The correct value sits just before the halo appears. For Motion, press Estimate motion first: it reads the blur length and direction from the crop’s spectrum and fills both sliders when it finds a clear peak.

Reading the split preview

The preview is a crop at one source pixel per screen pixel. Everything to the left of the line is the original, everything to the right is the result, and the line drags. Judge fine text, an eyelash, a brick edge, not a smooth sky, where no method can show anything.

The navigator in the top corner shows the whole picture with the crop marked. Drag it onto the part that matters, usually the subject’s eyes or the text you need to read, because that is the region the settings should be tuned on.

Strength

The solver minimises the difference between the blurred estimate and your photo, balanced against a total-variation prior that keeps the result piecewise smooth. Strength moves that balance. At the low end the prior dominates: noise stays down and some softness remains. At the high end the data dominates: more detail comes out, along with sensor noise, JPEG blocks and ringing around high-contrast edges. Most photos sit well around the middle; a clean low-ISO file from a camera can go higher, and a phone JPEG shot at night should go lower.

The processing runs on linear-light luminance only, and colour is scaled to match. That keeps chroma from ringing and avoids the coloured fringes a per-channel deconvolution produces.

Limits

Deconvolution inverts a blur; it does not create information. A blur larger than roughly 15 pixels has erased whole bands of the spectrum, and raising Strength there amplifies noise rather than recovering anything. A blur that varies across the frame, such as a portrait with a soft background or a rotation shake, has no single kernel to invert. A heavily compressed JPEG shows its 8 by 8 block grid once sharpened, because the grid is real detail as far as the maths is concerned.

A blurred face stays a blurred face. The search results that promise a sharp face from a hopeless one use a generative model that invents a plausible one, which is a different job with a different honesty. This page recovers what the file still holds, which on a mildly soft photo is more than most people expect.

Export

Download processes the full-resolution image in overlapping tiles with the same kernel and Strength as the preview, blends the tile edges, and writes the source format. Output is a re-encoded file, so EXIF data from the original is not carried over.

Frequently Asked Questions

It estimates the sharp picture that, once blurred by the kernel you chose, would produce the photo you loaded. Load a JPEG, PNG or WebP that is softly out of focus or shaken in one direction. The download keeps the source format and the full resolution.

Lens is a missed focus: every point became a small disc, so edges look evenly soft in all directions. Motion is camera or subject movement during the exposure: edges are smeared along one line and sharp across it. Soft is a general Gaussian haze, which suits a picture that was upscaled or passed through a heavy noise filter.

Blur of a few pixels disappears when a 4000 px photo is shrunk to fit a 600 px box, and so would any improvement. The preview shows a region at one source pixel per screen pixel, which is the only honest way to judge it. Drag the small navigator in the corner to move the crop.

It sets how hard the solver trusts the blurred data against a smoothness prior. Low values give a cautious result with little noise and some residual softness. High values pull out more detail and let noise, JPEG blocks and ringing through. Around the middle is right for most photos; raise it for clean, low-ISO sources.

A blur much larger than about 15 pixels, because those frequencies are gone from the file. Blur that changes across the frame, such as shallow depth of field or rotation shake, because one kernel cannot describe it. Heavily compressed JPEGs, whose block edges get amplified along with the detail. A blurred face will not become a sharp face; the AI tools that do that invent one.

Ringing means the kernel is wrong or Strength is too high. Lower the size slider until the halos collapse into a single edge, then lower Strength. For Motion, nudge Angle by a few degrees. Saturated highlights ring more than anything else and cannot be helped.

A straight motion blur leaves a regular gap pattern in the picture's spectrum. The estimator computes the cepstrum of the current crop, finds the strongest peak away from the origin, and reads the blur length and direction from its position. It works on textured regions and reports nothing when no clear peak exists.

Explore Our Tools

Browse all tools