Novus Examples, Real, documented example files for testing

Deblur Motion H: Base B (512px)

Base B with motion-h blur. Score a deblur tool against the clean reference in this group.

File: PNG · Deblur Set · 512 × 512 px
Use case: Deblur testingImage pipeline QA· Conversion set

Deblur Motion V: Base A (512px)

Base A with motion-v blur. Score a deblur tool against the clean reference in this group.

File: PNG · Deblur Set · 512 × 512 px
Use case: Deblur testingImage pipeline QA· Conversion set

Deblur Motion V: Base B (512px)

Base B with motion-v blur. Score a deblur tool against the clean reference in this group.

File: PNG · Deblur Set · 512 × 512 px
Use case: Deblur testingImage pipeline QA· Conversion set

Deblur Shake: Base A (512px)

Base A with shake blur. Score a deblur tool against the clean reference in this group.

File: PNG · Deblur Set · 512 × 512 px
Use case: Deblur testingImage pipeline QA· Conversion set

Deblur Shake: Base B (512px)

Base B with shake blur. Score a deblur tool against the clean reference in this group.

File: PNG · Deblur Set · 512 × 512 px
Use case: Deblur testingImage pipeline QA· Conversion set

Deeply Nested JSON

A deeply nested JSON document with objects inside arrays inside objects, for testing recursive parsing and path access.

File: JSON · JSON
Use case: JSON parsing

Preview of Defect Triage Grid (HTML) — Actual file preview for Defect Triage Grid (HTML)

Four radio groups - severity, likelihood, blast radius and confidence - that a triage rule combines into a priority. The groups share nothing but their layout, which makes it a good test of group-name resolution in a dense form.

File: HTML · Software Quality · 7 fields
Use case: Form testingForm parsing+3

Denoise Base A: Clean Reference (512px)

The clean reference image for denoise base A: a fruit still life on studio white. Diff the noisy variants in this set against this file to measure filter accuracy.

File: PNG · Denoise Set · 512 × 512 px
Use case: Denoise testingImage pipeline QA· Conversion set

Denoise Base B: Clean Reference (512px)

The clean reference image for denoise base B: a coffee mug on studio white. Diff the noisy variants in this set against this file to measure filter accuracy.

File: PNG · Denoise Set · 512 × 512 px
Use case: Denoise testingImage pipeline QA· Conversion set

Denoise Ground Truth: detail-chart

The clean reference for the detail-chart denoise set: no noise added, encoded at CRF 14. Every noisy clip in this group was produced from these exact pixels, so PSNR, SSIM and LPIPS against this file are meaningful rather than approximate.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Ground Truth: gradient-sky

The clean reference for the gradient-sky denoise set: no noise added, encoded at CRF 14. Every noisy clip in this group was produced from these exact pixels, so PSNR, SSIM and LPIPS against this file are meaningful rather than approximate.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Ground Truth: pan-city

The clean reference for the pan-city denoise set: no noise added, encoded at CRF 14. Every noisy clip in this group was produced from these exact pixels, so PSNR, SSIM and LPIPS against this file are meaningful rather than approximate.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Gaussian σ=15

Gaussian σ=15 applied to the detail-chart base plate with seed 9017. Moderate Gaussian noise, roughly a mid-ISO handheld shot. The level most denoise benchmarks use. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 19, where the light noise could otherwise be confused with compression artefacts.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Gaussian σ=30

Gaussian σ=30 applied to the detail-chart base plate with seed 9034. Heavy Gaussian noise where fine detail and noise overlap in amplitude, so recovery requires temporal information rather than spatial smoothing alone. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Gaussian σ=5

Gaussian σ=5 applied to the detail-chart base plate with seed 9000. Light sensor noise: the level a modern camera produces at base ISO. Subtle enough that an over-aggressive denoiser does more damage than the noise did. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 19, where the light noise could otherwise be confused with compression artefacts.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Gaussian σ=50

Gaussian σ=50 applied to the detail-chart base plate with seed 9051. Severe noise approaching the signal level. Included as the failure case: most denoisers hallucinate structure here, which is exactly what the paired reference exposes. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Multiplicative speckle

Multiplicative speckle applied to the detail-chart base plate with seed 9102. Multiplicative rather than additive noise, so its amplitude scales with local brightness: the pattern seen in ultrasound and radar. Additive-noise models systematically under-correct highlights. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Poisson shot noise

Poisson shot noise applied to the detail-chart base plate with seed 9119. Photon shot noise, signal-dependent and the physically correct model for low-light capture. Dark regions are proportionally far noisier than bright ones. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Salt and pepper 2%

Salt and pepper 2% applied to the detail-chart base plate with seed 9068. Two per cent of pixels forced to pure black or white: impulse noise from sensor faults and transmission errors. Defeats Gaussian-assuming filters, which smear each spike instead of rejecting it. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 19, where the light noise could otherwise be confused with compression artefacts.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: detail-chart, Salt and pepper 8%

Salt and pepper 8% applied to the detail-chart base plate with seed 9085. Dense impulse noise. A median filter handles this trivially and a Gaussian one cannot, so it separates the two families of denoiser immediately. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: gradient-sky, Gaussian σ=15

Gaussian σ=15 applied to the gradient-sky base plate with seed 9017. Moderate Gaussian noise, roughly a mid-ISO handheld shot. The level most denoise benchmarks use. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 19, where the light noise could otherwise be confused with compression artefacts.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: gradient-sky, Gaussian σ=30

Gaussian σ=30 applied to the gradient-sky base plate with seed 9034. Heavy Gaussian noise where fine detail and noise overlap in amplitude, so recovery requires temporal information rather than spatial smoothing alone. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: gradient-sky, Gaussian σ=5

Gaussian σ=5 applied to the gradient-sky base plate with seed 9000. Light sensor noise: the level a modern camera produces at base ISO. Subtle enough that an over-aggressive denoiser does more damage than the noise did. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 19, where the light noise could otherwise be confused with compression artefacts.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Denoise Input: gradient-sky, Gaussian σ=50

Gaussian σ=50 applied to the gradient-sky base plate with seed 9051. Severe noise approaching the signal level. Included as the failure case: most denoisers hallucinate structure here, which is exactly what the paired reference exposes. Paired with the clean ground truth in this group, so denoiser output can be scored numerically. Encoded at CRF 24 rather than 19: random noise is incompressible, and at this amplitude the codec's own artefacts sit far below the noise floor, so a coarser quantiser saves several megabytes without affecting any measurement.

File: MP4 · Denoise · 640x360
Use case: Video denoiseVideo QA· Conversion set

Explore the test library

Filter the library

5297 results