This page describes the results format used by COCO DensePose evaluation procedure. The results format mimics the annotation format detailed on the data format page. Please review the annotation format before proceeding.
Each algorithmically generated result is stored separately in its own result struct. This singleton result struct must contain the id of the image from which the result was generated (a single image will typically have multiple associated results). Results for the whole dataset are aggregated in a single array. Finally, this entire result struct array is stored to disk as a single JSON file (saved via gason in Matlab or json.dump in Python).
Example result JSON files are available in example results.
The data struct for each of the result types is described below. The format
of the individual fields below (
bbox, etc.) is the same as
for the annotation (for details see the data format page).
Bounding box coordinates
bbox are floats measured from the top left image
corner (and are 0-indexed). We recommend rounding coordinates to the nearest
tenth of a pixel to reduce the resulting JSON file size. The dense estimates
of patch indices and coordinates in the UV space for the specified bounding
box are stored in
uv_shape contains the shape of
uv_data array, it should be of size
(3, height, width), where
width should match the bounding box
uv_data should contain PNG-compressed patch indices and U and V
coordinates scaled to the range
An example of code that generates results in the form of a
pkl file can
be found in
We also provide an example script to convert
dense pose estimation results stored in a
pkl file into a PNG-compressed