Indirect deep structured learning for 3D human body shape and pose prediction

By Vince Tan, Ignas Budvytis, Roberto Cipolla. 2017

156 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

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

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

End-to-End Recovery of Human Shape and Pose (2017, methodology): “[41] infer SMPL parameters in a two-step approach that first learns a SMPL-to-silhouette decoder using synthetic data, and then learns an image-toSMPL encoder network with a fixed decoder, where the objective is to reconstruct the image silhouettes.”
Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild (2020, methodology): “Body Mesh Recovery Approaches based on regressing MANO parameters described in the previous subsection originate from works on body mesh recovery [3, 28, 22, 48, 42, 50, 41, 39, 21, 55, 25].”
Deep Learning-based Human Pose Estimation: A Survey (2020, unknown): “, [157] [158] [159] [160] [161] [162] [163] [164] [165] [166], because it is compatible with existing rendering engines.”
Monocular human pose estimation: A survey of deep learning-based methods (2020, methodology): “Tan et al. (2017) inferred SMPL parameters by ﬁrst training a decoder to predict silhouettes from SMPL parameters with synthetic data, and then learning an image encoder with the trained decoder.”
Learning to Estimate 3D Human Pose and Shape from a Single Color Image (2018, methodology): “It is interesting to note that a version of [43], which uses over 100k images (most of them synthetic) with ground truth pose and shape parameters to directly supervise the network (line ‘Direct’) is outperformed by our approach which does not have access to this data.”
Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop (2019, methodology): “This information can be used as input [37], intermediate representation [24, 27], or as supervision, by enforcing different reprojection losses [15, 24, 27, 34, 37].”
Single-Shot Multi-person 3D Pose Estimation from Monocular RGB (2017, background): “Some works split the problem in two: ﬁrst estimate 2D joints and then lift them to 3D [58, 54, 9, 66, 35, 69, 1, 52, 20, 32, 6, 26, 38, 57, 2], e.g ., by database matching, neural network regression, or ﬁtting the SMPL body model [30].”
STAR: Sparse Trained Articulated Human Body Regressor (2020, background): “This makes it useful to reason about 3D human body pose and shape given sparse measurements, such as IMU accelerations [11,12,26], sparse mocap markers [22,25] or 2D key points in images and videos [3,14,15,16,28,33,36,38].”
3D Hand Shape and Pose Estimation From a Single RGB Image (2019, methodology): “One straightforward solution is to follow the common approach used in human body shape estimation [53, 48, 37, 22], namely to regress low-dimensional parameters of a predefined deformable hand model, e.”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, methodology): “For example, by fitting the SCAPE or SMPL model to the detected 2D skeleton and other shape cues of an image [5, 28], or by regressing [27, 49, 51] the SMPL model using CNNs, the shape and pose parameters can be automatically obtained from a single image.”
FrankMocap: Fast Monocular 3D Hand and Body Motion Capture by Regression and Integration (2020, background): “Many monocular 3D body pose estimation approaches consider to predict 3D body keypoint locations from single images [41, 50, 52, 29, 38].”
Kimera: From SLAM to spatial perception with 3D dynamic scene graphs (2021, background): “…et al. 2017; Zanfir et al. 2018; Kolotouros et al. 2019; Yang and Carlone 2020), and learning-based methods, which infer the mesh directly from pixel information (Tan et al. 2017; Kanazawa et al. 2018; Omran et al. 2018; Pavlakos et al. 2018; Kolotouros et al. 2019b; Kolotouros et al. 2019).”
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].”
3D Dynamic Scene Graphs: Actionable Spatial Perception with Places, Objects, and Humans (2020, unknown): “53, 107, 109], and learning-based methods, which infer the mesh directly from pixel information [38, 44, 45, 77, 79, 96].”
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction (2019, background): “However, the slow running time, the reliance on a good initialization and the typical failures due to bad local minima have recently shifted the focus to learning-based approaches [15, 18, 28, 31, 39, 43], that regress pose and shape directly from images.”
VIBE: Video Inference for Human Body Pose and Shape Estimation (2019, methodology): “Recently, deep neural networks are trained to directly regress the parameters of the SMPL body model from pixels [21, 29, 45, 48, 55, 57].”
BodyNet: Volumetric Inference of 3D Human Body Shapes (2018, unknown): “On 3D metrics, our method significantly outperforms both direct and indirect learning of [14].”