期刊
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
卷 40, 期 12, 页码 3059-3066出版社
IEEE COMPUTER SOC
DOI: 10.1109/TPAMI.2017.2772922
关键词
3D modeling and reconstruction; fine-grained reconstruction; 3D shape from a single 2D image; deep learning
资金
- National Institutes of Health [R01 DC 014498]
- Human Frontier Science Program [RGP0036/2016]
- NATIONAL EYE INSTITUTE [R01EY020834] Funding Source: NIH RePORTER
- NATIONAL INSTITUTE ON DEAFNESS AND OTHER COMMUNICATION DISORDERS [R01DC014498] Funding Source: NIH RePORTER
Three-dimensional shape reconstruction of 2D landmark points on a single image is a hallmark of human vision, but is a task that has been proven difficult for computer vision algorithms. We define a feed-forward deep neural network algorithm that can reconstruct 3D shapes from 2D landmark points almost perfectly (i.e., with extremely small reconstruction errors), even when these 2D landmarks are from a single image. Our experimental results show an improvement of up to two-fold over state-of-the-art computer vision algorithms; 3D shape reconstruction error (measured as the Procrustes distance between the reconstructed shape and the ground-truth) of human faces is < .004, cars is .0022, human bodies is .022, and highly-deformable flags is .0004. Our algorithm was also a top performer at the 2016 3D Face Alignment in the Wild Challenge competition (done in conjunction with the European Conference on Computer Vision, ECCV) that required the reconstruction of 3D face shape from a single image. The derived algorithm can be trained in a couple hours and testing runs at more than 1,000 frames/s on an i7 desktop. We also present an innovative data augmentation approach that allows us to train the system efficiently with small number of samples. And the system is robust to noise (e.g., imprecise landmark points) and missing data (e.g., occluded or undetected landmark points).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据