Mathematical Problems in Engineering / 2013 / Article / Tab 2

Research Article

Matching Cost Filtering for Dense Stereo Correspondence

Table 2

Evaluation for stereo methods on all 27 Middlebury stereo pairs.

MethodAloeBaby1Baby2Baby3Bowling1Bowling2Cloth1Cloth2Cloth3Cloth4

HCN12.7111.1411.8117.8726.7019.109.7116.3711.1514.95
GIN13.4212.3912.8817.9827.3719.1910.3616.5611.3015.40
HCR8.194.997.249.7420.6914.384.6110.965.3410.66
GIR8.785.417.599.9920.2614.615.0311.435.4310.81

MethodFlowerpotsLampshade1Lampshade2Midd1Midd2MonopolyPlasticRocks1Rocks2Wood1

HCN23.6023.0330.9545.6641.6636.5143.6211.9012.2416.78
GIN23.4124.1332.6446.5842.9034.7847.8111.7211.8317.61
HCR18.4815.8623.4643.9537.3022.7135.605.725.195.26
GIR18.8116.6724.0144.3538.6225.0138.335.555.025.57

MethodWood2ArtBooksDollsLaundryMoebiusReindeerAE

HCN15.4326.2621.5917.3227.9820.3221.9621.79
GIN14.8326.4121.1016.6829.1920.0623.1222.28
HCR0.6418.6017.8511.9020.8014.688.1914.92
GIR0.5718.5917.5011.9622.8014.228.3615.38

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19.