NoW Benchmark
3d meshesImagesCustomIntroduced 2019-05-16
The goal of this benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods under variations in viewing angle, lighting, and common occlusions.
The dataset contains 2054 2D images of 100 subjects, captured with an iPhone X, and a separate 3D head scan for each subject. This head scan serves as ground truth for the evaluation. The subjects are selected to contain variations in age, BMI, and sex (55 female, 45 male).
Benchmarks
3D/Median Reconstruction Error3D/Mean Reconstruction Error (mm)3D/Stdev Reconstruction Error (mm)3D Face Modelling/Median Reconstruction Error3D Face Modelling/Mean Reconstruction Error (mm)3D Face Modelling/Stdev Reconstruction Error (mm)3D Face Reconstruction/Median Reconstruction Error3D Face Reconstruction/Mean Reconstruction Error (mm)3D Face Reconstruction/Stdev Reconstruction Error (mm)Face Reconstruction/Median Reconstruction ErrorFace Reconstruction/Mean Reconstruction Error (mm)Face Reconstruction/Stdev Reconstruction Error (mm)Facial Recognition and Modelling/Median Reconstruction ErrorFacial Recognition and Modelling/Mean Reconstruction Error (mm)Facial Recognition and Modelling/Stdev Reconstruction Error (mm)