Find files, editable templates and browser test targets by what you need to make or test. The directory below is cut by format; the two collections under it cut the same library by subject and by workflow.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-bridge.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate l-bridge.
A synthetic photographic plate of a landscape or architectural scene, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate l-bridge.
A canny edge map for the published plate storefront.png, 1216x832. Canny edge detection at low threshold 0.1 and high 0.3, run at the plate's own resolution so the edges land on the same pixels as the photograph they came from. Lit coverage measures 7.5% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.
A depth map for the published plate storefront.png, 1497x1024. Monocular depth from Depth Anything V2 (vitl), rendered at the plate's long edge rather than the 512-pixel default, so depth and colour can be compared per pixel without a resample in between. Lit coverage measures 97.9% of the frame. The plate and this map are the same scene at the same size, so they can be compared pixel for pixel rather than by eye.
A tangent-space surface normal map for the published plate storefront.png, 1216x832 - 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.
The scrub-preview sheet for the film in this group: 24 tiles in a 6x4 grid, one sampled per second, each 160x90. This is the form a player requests when a viewer drags the scrubber. A two-second clip yields two tiles and proves nothing about tiling; 24 seconds fills the grid.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-knight.
A synthetic photographic plate of a stylised rendered game scene or character, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate g-char-knight.
The same plate encoded once at JPEG quality 25. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
The same plate encoded once at JPEG quality 50. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
The same plate encoded once at JPEG quality 75. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
The same plate encoded once at JPEG quality 90. Blocking and ringing are bounded by that single pass, so a restorer can be scored against the PNG reference in this group rather than against an opinion Plate g-char-mage.
