Image restore

POST /api/image-restore5 quota units per call · cache hits free

Bring back life to a noisy or faded photo with a one-shot restore pass: edge-preserving bilateral denoise, CLAHE contrast equalisation, and unsharp masking. No ML model — pure classical CV.

One-shot restoration pipeline for old, noisy, or faded photos. Three OpenCV passes chained in order: 1. **Bilateral denoise** — removes sensor / scan noise while preserving edges (otherwise step 3 would amplify the noise). 2. **CLAHE** in LAB space — equalises contrast adaptively on the L channel so colour doesn't shift. 3. **Unsharp mask** — sharpens the now-cleaner image. Each pass exposes its own knobs (`denoiseStrength`, `claheClipLimit`, `sharpenAmount`), all with sensible defaults. Set `denoise=false` / `clahe=false` / `sharpen=false` to skip a stage entirely. Useful for: - Restoring scanned family photos. - Reviving over-compressed JPEGs. - Pre-processing scans before OCR (faded ink / yellowed paper). For ML-grade restoration (face super-resolution, colourisation) use a hosted model — those are out of scope here.

Inputs

Name	Type	Default	Description
image*	file	—	Input image bytes.
denoise	boolean	true	Whether to run the bilateral denoise pass.
denoiseStrength	number (1…150)	50	Bilateral filter colour + spatial sigma. Higher = stronger smoothing.
clahe	boolean	true	Whether to run the CLAHE contrast pass.
claheClipLimit	number (0.5…20)	2	CLAHE clip limit. Higher = stronger contrast.
sharpen	boolean	true	Whether to run the unsharp-mask pass.
sharpenAmount	number (0…3)	0.6	Unsharp mask amount. Higher = more aggressive sharpening.
format	enum (jpeg \| png)	"jpeg"	Output image format.

Response

Modes: binary, stream, json. Cache: yes (24h TTL).

Large outputs stream: responses over the 4 MiB cache limit are piped through as they are produced instead of buffered. They carry x-cache-skip: size and are never cached — identical follow-up calls recompute.

Every response carries x-cache (HIT / MISS / BYPASS), x-cache-signature (stable across identical inputs), and the rate-limit headers listed below.

Quota & limits

Cost per call	5 units against the 10,000-unit monthly quota. Cache hits are free — only cache misses decrement.
Burst limit	200 requests per rolling minute, shared across all tools.
Max request size	`15 MiB` (base64 inflates file payloads ~33% — the limit applies to the decoded bytes).
Max response size	`25 MiB`
Timeout	30s wall clock.
Rate-limit headers	`X-RateLimit-Limit`, `X-RateLimit-Remaining`, `X-RateLimit-Burst-Limit` on every response; `X-Quota-Warning` once 80% of the monthly quota is spent; `Retry-After` on 429s.

Errors

Errors are JSON with an error string; schema failures add a details object (Zod's flattened field errors).

Status	When	Body
400	Input fails the tool's schema (wrong type, missing required field, malformed base64) or the file bytes can't be parsed as the expected format.	{ "error": "invalid inputs", "details": { "fieldErrors": { … } } }
401	Missing or invalid X-Api-Key / X-Account-Id headers (or no session when called from the browser).	{ "error": "unauthorized" }
404	Unknown tool id, or calling /api/* on the website hostname instead of api.xtract.bot.	{ "error": "not found" }
413	Request body over the tool's max request size, or an image header declaring more megapixels than the tool's pixel budget.	{ "error": "…exceeds maxRequestBytes…" }
415	Content-Type isn't application/json on the json-body transport.	{ "error": "unsupported content-type; expected application/json" }
429	Monthly quota or the 200/min burst limit exhausted. Check Retry-After and the X-RateLimit-* headers.	{ "error": "monthly quota exceeded", "monthRemaining": 0, … }
5xx	Conversion engine failure. Safe to retry; if it persists, the input is hitting a bug — please report it.	{ "error": "…" }

Code samples

Built from the default example.

# Download or substitute the example input:
#   curl -O https://xtract.bot/examples/face-fixtures/face-small.png
IMAGE=$(base64 -w0 < face-small.png)

curl -X POST https://api.xtract.bot/api/image-restore \
  -H "Content-Type: application/json" \
  -H "Accept: application/octet-stream" \
  -H "X-Account-Id: $XTRACT_ACCOUNT_ID" \
  -H "X-Api-Key: $XTRACT_API_KEY" \
  -d '{
  "denoise": true,
  "clahe": true,
  "sharpen": true,
  "format": "jpeg",
  "image": "'"$IMAGE"'"
}'