Determination of 3D human body postures from a single view

By Hsi-Jian Lee, Zen Chen. 1985

How researchers see this paper

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

Citations in the corpus

End-to-End Recovery of Human Shape and Pose (2017, methodology): “Most methods make some assumption about the limb-length or proportions [4, 21, 32, 34].”
A survey on still image based human action recognition (2014, background): “…detectors to determine the occurrence of individual objects for action recognition [25,36,30,38], some works integrate objects with the scene as context, e.g., Zheng et al. [43] learned context-based classifiers, which uses image content from both the foreground and the background as the context.”
Pose-conditioned joint angle limits for 3D human pose reconstruction (2015, background): “Lee and Chen [18] recover pose by pruning a binary interpretation tree representing all possible body configurations.”
Synthesizing Training Images for Boosting Human 3D Pose Estimation (2016, background): “Analyzing human bodies in images and videos has been a research topic for many decades, with particular attention paid to estimation of human body poses [18, 25].”
Model-Based Estimation of 3D Human Motion (2000, methodology): “Index TermsÐMotion estimation, human motion estimation, deformable models, model-based tracking, physics-based modeling. æ”
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose (2016, background): “Estimating the full-body 3D pose of a human from a single monocular image is an open challenge, which has garnered significant attention since the early days of computer vision [18].”
Recovering 3D human body configurations using shape contexts (2006, background): “Lee and Chen [ 30 ], [31] preserve the ambiguity regarding foreshortening (closer endpoint of each link) in an interpretation tree and use various constraints to prune impossible configurations.”
Robust Estimation of 3D Human Poses from a Single Image (2014, methodology): “Given a 3D pose, we estimate the camera parameters by minimizing the L 1 -norm projection error.”
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image (2017, background): “Early approaches [19, 34, 25, 6] took advantage of anatomical knowledge of the human skeleton or joint angle limits to recover pose from a single image.”
Estimating human shape and pose from a single image (2009, methodology): “A perspective solution [15] predates Taylor and forms the basis of our initialization method.”
Semantic Graph Convolutional Networks for 3D Human Pose Regression (2019, background): “Lee and Chen [30] first investigated inferring 3D joints from their corresponding 2D projections.”
Estimating Anthropometry and Pose from a Single Uncalibrated Image (2001, methodology): “Concerning posture estimation and tracking, methods have been presented that use either one [4, 6, 17 , 21], or multiple cameras [1, 7, 9, 13, 14, 16].”
Pictorial Human Spaces: How Well Do Humans Perceive a 3D Articulated Pose? (2013, methodology): “The synchronization between the two cameras is done automatically by the system.”
On Self-Contact and Human Pose (2021, background): “Lee and Chen [25] approximate the human body as a set of line segments and avoid collisions between the limbs and torso.”
Kinematic jump processes for monocular 3D human tracking (2003, methodology): “Skeletal reconstruction methods recover an interpretation tree of possible 3D joint positions, based on user-specified image joint positions [8, 17].”
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video (2015, background): “, non-rigid structure from motion (NRSFM), and human pose recovery models based on known skeletons [20, 43, 47, 30, 21] or sparse representations [32, 15, 2, 55, 56].”
A Survey of Computer Vision-Based Human Motion Capture (2001, background): “In the work by Lee and Chen [82] the positions of the joints in the image and the 3D length of each segment are known beforehand.”