Skip to content
Novus Examples
png579.8 KB

S plate: surface normal map

A tangent-space surface normal map for the published plate s-plate.png, 1024x1024 - the same size as the plate, so the two compare pixel for pixel with no resample in between. RGB encodes the XYZ surface direction remapped from -1..1 into 0..255. Decoded back to vectors this file measures a mean length of 0.9957, which is the number to check your own decode against: a reader that transposes the channels or inverts the remap still produces a plausible-looking image, and lights the surface the wrong way.

Preview of S plate: surface normal map

Specifications

Width
1024
Height
1024
Mean Vector Length
0.9957
Min Vector Length
0.9875
Max Vector Length
1.0092
Derivation Kind
normal
Encoding
tangent space, RGB = XYZ remapped from -1..1 into 0..255
Source Plate
s-plate.png
Synthetic
true
Disclosure
Derived from an AI-generated plate. Synthetic, not a photograph of a real scene.
Schema Version
1
Alt Text
A plated main course on a restaurant table from above, garnish and sauce, natural window light

Testing contract

Expected to pass
Scenario
Open this map and the published plate s-plate.png, compare their dimensions, then decode the RGB back to vectors and measure their length.
Expected result
Both are 1024x1024, so the map and the photograph compare pixel for pixel with no resample in between. Decoded as (RGB / 255 * 2 - 1) the vectors have a mean length of 0.9957: a decode that transposes the channels or inverts the remap still yields a plausible image, and this number is what separates the two.

What is a .png file?

PNG (Portable Network Graphics) is a raster image format using lossless DEFLATE compression. It supports full 8- or 16-bit-per-channel truecolor, palette, and greyscale modes with an optional alpha channel, but no animation. It is the standard choice for screenshots, logos, and graphics with sharp edges or transparency.

How to use this file

Use an example PNG to test image decoders, alpha-compositing, thumbnail generators, and format converters, or to verify that a pipeline preserves transparency and color depth on round-trip.

How to use this file for testing

“S plate: surface normal map” is a deterministic Novus Examples fixture for PBR material testing. Complete PBR material sets (base colour, normal, roughness, metallic, ambient occlusion, and height) for testing material-generation models and physically-based renderers channel by channel.

Documented properties for this file: 1024×1024 · tangent space, RGB = XYZ remapped from -1..1 into 0..255. 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.

For image AI or enhancement tools, run the model or filter on this file and diff against the clean or ground-truth companion in the same group when available. Keep seeds and documented damage parameters in your evaluation notes so regressions are attributable.

Code examples

<img src="s-plate-normal.png" alt="Example image" width="640" loading="lazy">

Generated by generation/comfy_normal_wave.py. Free for any use, no attribution required, license.