- P
NoW Benchmark Dataset
- paperswithcode.com
Updated Jun 2, 2021
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteSoubhik Sanyal; Timo Bolkart; Haiwen Feng; Michael J. Black (2020). NoW Benchmark Dataset [Dataset]. https://paperswithcode.com/dataset/now-benchmarkDataset updatedJun 2, 2021AuthorsSoubhik Sanyal; Timo Bolkart; Haiwen Feng; Michael J. BlackDescriptionThe 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).
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailThe 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).