EUROGRAPHICS 2012
Michael Tao, Jiamin Bai, Pushmeet Kohli, Sylvain Paris
Instructions: click desired image to view full-sized image.
HD Timing Performances
(4K: 4096 x 2304)
Pair 1 |
Frame 2![]() |
Our algorithm without sublinear optimization![]() |
Our Sublinear Scheme![]() |
128 x 72![]() |
256 x 144![]() |
512 x 288![]() |
Timings |
(1080P: 1920 x 1080 Resolution)
Pair 1 |
Frame 2![]() |
Our algorithm without sublinear optimization![]() |
Our Sublinear Scheme![]() |
480x270 optimization![]() |
960x540 optimization![]() |
1920x1080 optimization![]() |
Timings |
|
Pair 2 |
Frame 2![]() |
Our algorithm without sublinear optimization![]() |
Our Sublinear Scheme![]() |
480x270 optimization![]() |
960x540 optimization![]() |
1920x1080 optimization![]() |
Timings |
|
Pair 3 |
Frame 2![]() |
Our algorithm without sublinear optimization![]() |
Our Sublinear Scheme![]() |
480x270 optimization![]() |
960x540 optimization![]() |
1920x1080 optimization![]() |
Timings |
|
Pair 4 |
Frame 2![]() |
Our algorithm without sublinear optimization![]() |
Our Sublinear Scheme![]() |
480x270 optimization![]() |
960x540 optimization![]() |
1920x1080 optimization![]() |
Timings |
|
Pair 4 |
Frame 2![]() |
Our algorithm without sublinear optimization![]() |
Our Sublinear Scheme![]() |
480x270 optimization![]() |
960x540 optimization![]() |
1920x1080 optimization![]() |
Timings |
Middlebury Flow Quality Performances
Refer to Figure 5 for descriptions of each image.
Dimetrodon |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: .323) ![]() |
Our algorithm followed by Sun et al. 2010 |
Sun et al. 2010 only (RMSE: .166) ![]() |
ground truth![]() |
||
Grove 2 |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: .580) ![]() |
Our algorithm followed by Sun et al. 2010 (RMSE: .316) ![]() |
ground truth![]() |
|||
Grove 3 |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: 1.458) ![]() |
Our algorithm followed by Sun et al. 2010 (RMSE: 1.372) ![]() |
Sun et al. 2010 only (RMSE: 1.398) ![]() |
ground truth![]() |
||
Hydrangea |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: .539) ![]() |
Our algorithm followed by Sun et al. 2010 (RMSE: .399) ![]() |
Sun et al. 2010 only (RMSE: .398) ![]() |
ground truth![]() |
||
Urban 2 |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: 1.436) ![]() |
Our algorithm followed by Sun et al. 2010 (RMSE: .854) ![]() |
Sun et al. 2010 only (RMSE: .804) ![]() |
ground truth![]() |
||
Urban 3 |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: 2.064) ![]() |
Our algorithm followed by Sun et al. 2010 (RMSE: 1.487) ![]() |
Sun et al. 2010 only (RMSE: 1.166) ![]() |
ground truth![]() |
||
Venus |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: .568) ![]() |
Our algorithm followed by Sun et al. 2010 (RMSE: .429) ![]() |
Sun et al. 2010 only (RMSE: .426) ![]() |
ground truth![]() |
||
Whale |
Frame 2![]() |
Our algorithm without sublinear optimization (RMSE: .383) ![]() |
Our algorithm followed by Sun et al. 2010 (RMSE: .271) ![]() |
Sun et al. 2010 only (RMSE: .272) ![]() |
ground truth![]() |
HD Image credits:
Big Buck Bunny. Dir. Sacha Goedegebure. YouTube. Blender Foundation, 2008.
Middlebury Image credits:
Middlebury Computer Vision Group
NOTE: these images are JPEGs with maximum quality to minimize file size