iccv iccv2013 iccv2013-273 iccv2013-273-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ibrahim Radwan, Abhinav Dhall, Roland Goecke
Abstract: In this paper, an automatic approach for 3D pose reconstruction from a single image is proposed. The presence of human body articulation, hallucinated parts and cluttered background leads to ambiguity during the pose inference, which makes the problem non-trivial. Researchers have explored various methods based on motion and shading in order to reduce the ambiguity and reconstruct the 3D pose. The key idea of our algorithm is to impose both kinematic and orientation constraints. The former is imposed by projecting a 3D model onto the input image and pruning the parts, which are incompatible with the anthropomorphism. The latter is applied by creating synthetic views via regressing the input view to multiple oriented views. After applying the constraints, the 3D model is projected onto the initial and synthetic views, which further reduces the ambiguity. Finally, we borrow the direction of the unambiguous parts from the synthetic views to the initial one, which results in the 3D pose. Quantitative experiments are performed on the HumanEva-I dataset and qualitatively on unconstrained images from the Image Parse dataset. The results show the robustness of the proposed approach to accurately reconstruct the 3D pose form a single image.
[1] A. Agarwal and B. Triggs. 3D Human Pose from Silhouettes by Relevance Vector Regression. In CVPR 2004, pages II– 882 II–888, 2004.
[2] A. Agarwal and B. Triggs. Learning to track 3D human motion from silhouettes. In ICML ’04. ACM, 2004.
[3] A. Agarwal and B. Triggs. Recovering 3D Human Pose from Monocular Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(1):44–58, 2006. – 2Morequalitativeresults can be found at http://staff. e stem- uc .edu .au/ ibrahim/ 3dmode l .
[4] M. Andriluka, S. Roth, and B. Schiele. Monocular 3D Pose Estimation and Tracking by Detection. In CVPR 2010, pages 623–630, 2010.
[5] L. Bo and C. Sminchisescu. Twin Gaussian Processes for Structured Prediction. IJCV, 87(1–2):28–52, 2010.
[6] L. Bo, C. Sminchisescu, A. Kanaujia, and D. N. Metaxas. Fast Algorithms for Large Scale Conditional 3D Prediction. In CVPR 2008, 2008.
[7] C. A. Bouman. CLUSTER: an unsupervised algorithm for modeling Gaussian mixtures, 2005. http : / / cobweb .e cn .purdue .edu / ˜ bouman / s o ftware / clust e r/ .
[8] C. Bregler, A. Hertzmann, and H. Biermann. Recovering Non-Rigid 3D Shape from Image Streams. In CVPR 2000, pages 690–696, 2000.
[9] B. Daubney and X. Xie. Tracking 3D Human Pose with Large Root Node Uncertainty. In CVPR 2011, pages 1321 1328, 2011.
[10] P. Doll a´r, P. Welinder, and P. Perona. Cascaded pose regression. In CVPR 2010, pages 1078–1085, 2010.
[11] I. Radwan, A. Dhall, J. Joshi, and R. Goecke. Regression Based Pose Estimation with Automatic Occlusion Detection and Rectification. In ICME 2012, pages 121–127, 2012.
[12] D. Ramanan. Learning to Parse Images of Articulated Bodies. In NIPS, 2006.
[13] L. Sigal, A. Balan, and M. Black. HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion. IJCV, 87(1– 2):4–27, 2010.
[14] L. Sigal and M. J. Black. Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation, booktitle = CVPR 2006, pages = 2041–2048, year = 2006.
[15] E. Simo-Serra, A. Ramisa, G. Aleny `a, C. Torras, and F. Moreno-Noguer. Single Image 3D Human Pose Estimation from Noisy Observations. In CVPR 2012, pages 2673– 2680, 2012.
[16] C. J. Taylor. Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image. In CVPR 2000, pages 677–684, 2000.
[17] C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization method. IJCV, 9(2): 137–154, 1992.
[18] J. Valmadre and S. Lucey. Deterministic 3D Human Pose Estimation Using Rigid Structure. In ECCV 2010, pages 467– 480, 2010.
[19] X. K. Wei and J. Chai. Modeling 3D Human Poses from Uncalibrated Monocular Images. In ICCV 2009, pages 1873– 1880, 2009.
[20] Y. Yang and D. Ramanan. Articulated pose estimation with flexible mixtures-of-parts. In CVPR 2011, pages 1385–1392, 2011.
[21] Y. Yang and D. Ramanan. Articulated Human Detection with Flexible Mixtures-of-Parts. IEEE Transactions on PAMI, PP(99), 2012. 11889955