Stereo and Depth-from-Defocus Dataset 1: Patio

patio

Spanish patio: The original POV-Ray scene

From the original page:

This is a remake of an old scene, tried as a way to recover inspiration. The architecture uses various isosurfaces, and the rest is mostly CSG and some height_fields. To generate the palm trees I used the TOMTREE include file (required if you want to render this scene), with the help of POVTree (mirror), a java front-end for TOMTREE.

Copyright 2012 Jaime Vives Piqueres (jaime-at-ignorancia-dot-org)

Stereo and Depth-from-Defocus dataset

New! A second dataset is available, based on another POV-Ray scene by Jaime Piqueres: office.

Images

Here are JPEG-encoded previews for all the images in the dataset. The dataset includes better quality images, encoded as 16-bits 1152x864 PNG. Click on low-resolution images to get a high-resolution preview.

Note that there are small low-frequency illumination differences between the left and right images, which are due to radiosity computation (if someone knows how to share the radiosity computations between several views, please tell me).

All-in focus

patio_stereo1_all patio_stereo2_all

Focus on the background tree, large and small depth-of-focus

patio_stereo1_far patio_stereo2_far patio_stereo1_far2 patio_stereo2_far2

Focus on the fountain, large and small depth-of-focus

patio_stereo1_near patio_stereo2_near patio_stereo1_near2 patio_stereo2_near2

Depth, disparity and occlusion map ground truth

patio_stereo12.mx patio_stereo21 patio_stereo12.occ patio_stereo21.occ

Stereo and focal blur parameters

The interocular is 8 (see variable half_interocular in the pov files), and the convergence (or zero-disparity) distance (see variable convergence_dist in the pov files) is 320.

The *_near images are focused on the fountain (disparity=10.1768), the *_far images are focused on the tree in the back (disparity=14.7377), and the *_all images are all-in-focus.

The images with a small depth-of-focus were rendered with an aperture setting of 10, which means that the iris is a disc with diameter 40 (5 times the interocular) in world units.

The images with a larger depth-of-focus were rendered with an aperture setting of 5, which means that the iris is a disc with diameter 20 (2.5 times the interocular) in world units.

Reference

If you use this dataset, please cite the original publication where it appeared:

F. Devernay, S. Pujades and V. Ch.A.V., ``Focus mismatch detection in stereoscopic content'', Stereoscopic Displays & Applications XXIII, Woods, Holliman, Favalora (eds.), Proc. SPIE 8288, paper 8288-12, 2012 (HAL, presentation video).

We are also preparing a journal paper which extends the original paper with new interesting results, and hope it will be published in 2013. Please check out my publication list to see if it's already there.

Download

Re-rendering the dataset

Here are the instructions if you want to re-render the images from the original POV-Ray files. This way, you can adjust the camera parameters to your needs.

POV-Ray files

The files can be rendered using MegaPOV 1.2.1 with the annotation patch, and POV-Ray 3.7 RC6 (POV-Ray 3.6 generates visible artifacts between the left and right views). On Mac OS X, MegaPOV has to be compiled with GCC 4.2 (not LLVM-GCC or clang), or the rendering will be incorrect (I have instructions to install GCC 4.2 on recent Mac OS X).

Rendering

If no radiosity is applied, the rendering will be completely wrong: the shadowed aread (under the arcades) will be very dark.

In order to apply radiosity:

Change in patio/patio.pov the line

#declare usar_rad=0;

to

#declare usar_rad=2;

then, run one rendering. This will save a radiosity file "patio.rad" in the current directory.

For subsequent renderings from the same point of view (it is a good idea to render the left and right views in separate directories), change the line to

#declare usar_rad=1;

This will load the radiosity file and thus save computations.

All-in-focus view are rendered without focal blur, but with antialiasing (thus the options +A0.0 +J0.0 for the patio_stereo*_all.png images, which mean to perform 3x3 antialiasing on every pixel). The +FN16 option means to render 16-bits PNG images.

Left view:

Right view (+K0.0 is changed to +K1.0):

Ground-truth disparity and occlusion maps

The ground truth disparity map can be obtained using the VLPovUtils utilities. Here are the commands to produce this data, once the patio_stereo1_all and patio_stereo2_all scene have been rendered.

The first command computes the motion field and occlusion maps. The results are stored in patio-left/patio_stereo1_all.patio_stereo2_all.mx.tif, patio-left/patio_stereo1_all.patio_stereo2_all.occ.tif, patio-right/patio_stereo2_all.patio_stereo1_all.mx.tif, patio-right/patio_stereo2_all.patio_stereo1_all.my.tif, patio-right/patio_stereo2_all.patio_stereo1_all.occ.tif. The disparity maps are in the *.mx.tif files (stored as 32-bit floating point TIFF images) and the occlusion maps in the *.occ.tif files (stored as 8-bit grayscale TIFF files, converting them to PNG saves a lot of disk space).

The stereo disparity corresponding to the two focus distances can be obtained using the vlpov_project utility. The focal points are (-270,-20,270) [far] and (0,-6,0) [near] in POV-Ray coordinates. Note the Z coordinate of the 3D points has to be reversed, due to the left-handedness of POV-Ray's reference frame (see the code of function vlpov_get_cam in vlpovutils). The pixel coordinates of each points are in the first two columns, and the disparities (14.7 and 10.2) are in the fourth column of the output (last column, the vertical disparity, is almost zero):

Valid XHTML 1.1! Valid CSS! Level Double-A conformance icon, W3C-WAI Web Content Accessibility Guidelines 1.0