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.
Page 95 of 98; 24 results per page.
A canny edge map for the published plate v-train-plat.png, 1024x1024. 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 11.0% 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 v-train-plat.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 0.997, 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.
A canny edge map for the published plate v-truck-artic.png, 1024x1024. 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 8.5% 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 clean 512x512 crop of articulated lorry at a distribution depot loading bay, morning light, taken from the published plate v-truck-artic.png before anything was added to it. This is the ANSWER KEY for its group: the object in the source file was composited onto this image, so this is exactly what was behind it. Nothing else in the group came from a second tool's guess.
The same view of articulated lorry at a distribution depot loading bay, morning light, with a foreign object composited over 8.83% of the frame as one long thin region, where growing the mask by 12 pixels more than doubles the area it covers. This is the file an object-removal tool is given. Outside the mask it is byte-identical to the clean plate beside it, so any difference a tool leaves there is damage it did rather than content it was handed.
Articulated lorry at a distribution depot loading bay, morning light, with the object taken back out by Stable Diffusion 1.5 inpainting and the gap reconstructed from the surrounding context alone - the masked latents are erased before sampling, so the model never saw what it was painting over. Inside the mask it differs from the source by 55.181/255 and from the ground-truth plate by 63.287/255; the second number is NOT expected to be small, because an inpainter invents plausible content rather than recovering what was there. Beyond a 16-pixel ring around the mask the frame changes by only 6.781/255, which is the full-frame VAE round trip and not an edit.
The exact footprint of the object sitting over articulated lorry at a distribution depot loading bay, morning light, as an 8-bit mask covering 8.83% of the frame as one long thin region, where growing the mask by 12 pixels more than doubles the area it covers. It holds only the values 0 and 255. The footprint is what DREW the object, so it is ground truth by construction rather than a segmentation of it. Hard-edged on purpose: a feathered edge has no exact footprint, and the exactness is the point of shipping it.
A tangent-space surface normal map for the published plate v-truck-artic.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 0.9964, 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.
A canny edge map for the published plate v-van-delivery.png, 1024x1024. 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 7.3% 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 v-van-delivery.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 0.9955, 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 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-voxel-city.
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-voxel-city.
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-voxel-city.
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-voxel-city.
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-voxel-city.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate g-voxel-city.
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 s-warehouse-a.
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 s-warehouse-a.
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 s-warehouse-a.
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 s-warehouse-a.
A synthetic photographic plate of an interior or storefront with no people, 1024x1024, lossless PNG. This is the reference every lossy variant in this group is derived from Plate s-warehouse-a.
The same plate as WebP at quality 85, for format-handling coverage beside the PNG and JPEG encodings of identical pixels Plate s-warehouse-a.
A canny edge map for the published plate warehouse-clip.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 9.3% 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 dense pose map for the published plate warehouse-clip.png, 748x512. DensePose body-part segmentation, which labels regions of every person it finds rather than returning a skeleton, so background figures are labelled as well as the subject. Lit coverage measures 100.0% 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.
