Estimating human shape and pose from a single image

By Peng Guan, Alexander Weiss, Alexandru O. Balan, Michael J. Black. 2009

447 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

End-to-End Recovery of Human Shape and Pose (2017, methodology): “Methods that output more than 3D joints: There are multiple methods that fit a parametric body model to manually extracted silhouettes [8] and a few manually provided correspondences [12, 14].”
Picture: A probabilistic programming language for scene perception (2015, background): “There has been notable work in model-based approaches [13, 27] for 3D human pose estimation, which served as an inspiration for the program we describe in this section.”
Deep Volumetric Video From Very Sparse Multi-view Performance Capture (2018, methodology): “Additional improvements have been proposed using kinematic skeletons [26, 27], segmentation of moving subjects [28–30, 27, 31, 32] and human parametric models [33–39], even enabling single-view reconstruction [40– 44].”
Unite the People: Closing the Loop Between 3D and 2D Human Representations (2017, background): “More recently, these representations have taken new popularity in approaches that fit detailed surfaces of a body model to images [4, 14, 16, 25, 44].”
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016, methodology): “Unlike previous work [14,15], we provide an interpenetration term that is diﬀerentiable with respect to body shape and pose.”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, unknown): “In the past, this usually involved inferring a 3D human pose by optimizing an energy function derived from image information, such as silhouettes [6, 14, 21, 22, 25, 31, 44, 49, 60], trajectories [75], cm im”
Tex2Shape: Detailed Full Human Body Geometry From a Single Image (2019, methodology): “In early works 2D poses have been entirely or partially manually clicked [14, 62, 21, 42], later the process was automated [9, 28] with 2D landmark detections from deep neural networks [37, 18, 11].”
End-to-End Human Pose and Mesh Reconstruction with Transformers (2020, methodology): “Since it is challenging to regress the pose and shape coefficients directly from an input image, recent works further propose to leverage various human body priors such as human skeletons [21, 34] or segmentation maps [29], and explore different optimization strategies [19, 17, 46, 12] and temporal ”
PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop (2021, unknown): “In the main manuscript, we report results of our approach in a variety of evaluation metrics for quantitative comparisons with the state of the art, where all metrics are computed in the same way as previous work [6, 15, 9] in the literature.”
A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose (2021, unknown): “This enables real-time reconstructions from single images [8, 18], detailed texturing and displacement mapping [4, 6], and alleviates manual rigging [3].”
Measuring and reducing observational latency when recognizing actions (2011, methodology): “Our method could be extended to 2011 IEEE International Conference on Computer Vision Workshops 978-1-4673-0063-6/11/$26.00 c©2011 IEEE 422 traditional imagery, but that would require some method of estimating pose, such as [7, 20].”
Sim2real transfer learning for 3D human pose estimation: motion to the rescue (2019, background): “Similar to our work, state-of-the-art approaches often rely on parametric body models to incorporate strong priors on 3D poses [5, 7, 8, 22, 24, 34, 40, 43, 52, 57, 74].”
Balloon Shapes: Reconstructing and Deforming Objects with Volume from Images (2013, methodology): “We could also rely on cosegmentation methods [20] to segment the same object in both images, or use a similar strategy to [9] alternating between estimating the shape and the segmentation.”
Learning to Estimate 3D Human Pose and Shape from a Single Color Image (2018, methodology): “Most approaches rely on iterative optimization, attempting to estimate a full body 3D shape that is consistent with 2D image observations, like silhouettes, edges, shading, or 2D keypoints [41, 14].”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, background): “It is the state-of-the-art among available methods for single-view pose and shape estimation[31, 4, 16, 60, 63].”
Multi-Garment Net: Learning to Dress 3D People From Images (2019, background): “current statistical models can not represent clothing, most works [7, 26, 40, 68, 48, 32, 22, 67, 31, 50, 8, 33, 44, 46] are restricted to inferring body shape alone.”
MonoCap: Monocular Human Motion Capture using a CNN Coupled with a Geometric Prior (2017, unknown): “, [28], [63], [64]), the current approach leverages CNNs to learn better 2D representations and sparsity-driven 3D pose optimization to allow efficient and global inference.”
Learning to Dress 3D People in Generative Clothing (2019, background): “Most approaches [9, 17, 23, 26, 27, 30, 36, 38, 46] output 3D body meshes from images, but not clothing.”
Learning to Reconstruct People in Clothing From a Single RGB Camera (2019, methodology): “Early RGB-based methods were restricted to estimating the parameters of a body model, and required multiple views [8] or manually clicked points [30, 86, 39, 63].”
BodyNet: Volumetric Inference of 3D Human Body Shapes (2018, unknown): “Earlier work [39,40] proposed to optimize pose and shape parameters of the 3D deformable body model SCAPE [41].”