Hide/Show Apps

Frankenstein3d: human body reconstruction from limited number of points

Taştan, Oğuzhan
We propose a novel approach for reconstructing high-resolution 3D human body models from extremely small number of 3D points which represent body parts. We leverage a database of high-resolution 3D models of 100 humans varying from each other by physical attributes such as age, weight, size etc. We, first, divide the bodies in database into seven semantic regions. Then, for each input region consisting of maximum 40 points, we search the database for the best matching body part. For the matching criterion, we use the distance between novel point-base features of input points and body parts in the database. We further combine the matched parts from different bodies into one body which result in a high-resolution human body, with the help of Laplacian deformation. To evaluate our results, we pick points from each part of the ground-truth human body models, then reconstruct them using our method and compare the resulting bodies with corresponding ground-truths. Also, our results are compared with ARAP-based results. In addition, we run our algorithm with noisy data to test robustness of our method and run it with input points whose body parts are manually edited, which produces plausible human bodies that do not even exist in our database. Our experiments verify qualitatively and quantitatively that the proposed approach reconstructs human bodies with different physical attributes from small number of points successfully and prove that our method is robust to noisy data.