Denoise Input — pan-city, Gaussian σ=5
Gaussian σ=5 applied to the pan-city 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.
Browser-playable test video · 1 seconds
Specifications
- Resolution
- 640x360
- Fps
- 24
- Duration
- 1s
- Noise Type
- gaussian
- Noise Amount
- 5
- Seed
- 9000
- Role
- denoise input
- Codec Artefacts
- minimal — encoded near-transparent
- Reference
- vid-denoise-pan-city-gt
- Crf
- 19
- Base Plate
- pan-city
Testing contract
Expected to pass- Scenario
- Denoise the clip and score the result against the ground-truth reference named in its specs.
- Expected result
- The input carries gaussian noise at amount 5, generated from fixed seed 9000, over the pan-city plate at 640x360 24 fps. The reference is vid-denoise-pan-city-gt. Because the seed is fixed the noise field is reproducible exactly, so two runs of the same denoiser must score identically; codec artefacts are minimal — encoded near-transparent, so a score difference across the noise ladder is attributable to the noise alone.
What is a .mp4 file?
MP4 (MPEG-4 Part 14) is the dominant container for digital video, holding video, audio, subtitle, and metadata tracks in a tree of typed boxes. `ftyp` declares the brand, `moov` carries the sample tables that make seeking possible, and `mdat` holds the media; when an encoder writes `moov` last, playback cannot begin until the file has fully downloaded, which a faststart remux fixes. It derives from Apple's QuickTime format, generalized by ISO into the ISOBMFF base that MOV, 3GP, and HEIF share.
How to use this file
Use an example MP4 to test box parsing and track detection, seeking, range-request streaming, and transcode or thumbnail pipelines: verifying that a file with a trailing `moov` box is still handled, and that codec support is checked per track rather than inferred from the extension.
How to use this file for testing
“Denoise Input — pan-city, Gaussian σ=5” is a deterministic Novus Examples fixture for Video denoise, Video QA. Clips degraded with documented noise type, sigma, and seed, each shipped beside the exact high-quality source it came from, so a denoiser's output can be scored, not eyeballed.
Documented properties for this file: seed 9000 · denoise input · gaussian · 1s · 24 fps. Compare results against paired or grouped companions on this page when present (clean↔damaged, searchable↔scanned, or format twins) so scores stay reproducible across runs.
Download the file once, keep the path stable in CI or local scripts, and treat the spec table as the contract: dimensions, seeds, field lists, and roles are intentional. Corrupt or invalid samples are labelled as such, expect parsers to fail loudly rather than silently accept them.
Media fixtures are short and synthetic by design. Prefer waveform or transcript ground truth in the same group when measuring ASR, trim, upscale, or sync tools; do not assume broadcast-quality masters.
Code examples
<video controls preload="metadata" width="640" src="pan-city-gauss-05.mp4"></video>Related files
- mp4Denoise Ground Truth — detail-chartThe 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.
- mp4Denoise Ground Truth — gradient-skyThe 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.
- mp4Denoise Input — detail-chart, Gaussian σ=15Gaussian 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.
- mp4Denoise Input — detail-chart, Gaussian σ=30Gaussian 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.
- mp4Denoise Input — detail-chart, Gaussian σ=5Gaussian 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.
- mp4Denoise Input — detail-chart, Gaussian σ=50Gaussian 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.
Generated by generation/video_ai_suites.py. Free for any use, no attribution required, license.