Pose-conditioned joint angle limits for 3D human pose reconstruction

By Ijaz Akhter, Michael J. Black. 2015

479 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Space-Time Representation of People Based on 3D Skeletal Data: A Review (2016, methodology): “The PosePrior dataset [69] is the newest MoCap dataset that includes an extensive variety of”
End-to-End Recovery of Human Shape and Pose (2017, methodology): “Two stage methods first predict 2D joint locations using 2D pose detectors [30, 49, 54] or ground truth 2D pose and then predict 3D joint locations from the 2D joints either by regression [26, 29] or model fitting, where a common approach exploits a learned dictionary of 3D skeletons [2, 34, 47, 37,”
Single Image 3D Interpreter Network (2016, background): “The skeleton model can capture geometric changes of articulated objects [9,25], like a human body or the base of a swivel chair.”
Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image (2017, methodology): “More recent methods [13, 28, 3] have focused on learning a prior statistical model of the human body directly from 3D mocap data.”
HuMoR: 3D Human Motion Model for Robust Pose Estimation (2021, methodology): “For training the CVAE, we use the recommended training split (save for TCD Hands [14] which contains mostly hand motions): CMU [6], MPI Limits [2], TotalCapture [35], Eyes Japan [20], KIT [24], BMLrub [34], BMLmovi [10], EKUT [24], and ACCAD [1].”
Fusing 2D Uncertainty and 3D Cues for Monocular Body Pose Estimation (2016, background): “Let I : [1,W ]× [1, H]× [1, 3]→ [0, 1] be the input RGB image, X : [1,W ]× [1, H]× [1, J ]→ [0, 1] the probability maps encoding the probability of observing each one of J body joints at any given image location, and y ∈ R the vector of 3D joint locations.”
A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Image (2016, methodology): “To further verify that our proposed approach is better than state-of-the-art algorithms, we compare our method with the one proposed in [36].”
Sim2real transfer learning for 3D human pose estimation: motion to the rescue (2019, methodology): “One straightforward approach is to ‘lift’ 2D poses into 3D, using either dictionaries or direct regression [3, 44, 47, 64, 79, 85, 88, 93].”
Monocular 3D Human Pose Estimation Using Transfer Learning and Improved CNN Supervision (2016, background): “The weak projection model yields closed form, in contrast to more expensive optimization solutions [11, 88, 2].”
Monocular Total Capture: Posing Face, Body, and Hands in the Wild (2018, methodology): “age) [58, 44, 4, 60, 9, 35, 33, 73, 27, 36, 69] using available 2D and 3D human pose datasets [5, 28, 1, 22, 25].”
Learning to Estimate 3D Human Pose and Shape from a Single Color Image (2018, unknown): “Akhter & Black [2]* 181.”
Learning Camera Viewpoint Using CNN to Improve 3D Body Pose Estimation (2016, background): “Akhter et al [1] proposed a new framework to estimate 3D pose from ground truth 2D pose.”
Ordinal Depth Supervision for 3D Human Pose Estimation (2018, unknown): “Akhter & Black [1]* (CVPR’15) 199.”
Keep It SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image (2016, methodology): “Akhter and Black [4] take a similar approach but add a novel pose prior that captures pose-dependent joint angle limits.”
A Simple Yet Effective Baseline for 3d Human Pose Estimation (2017, methodology): “2d/3d positions Our first design choice is to use 2d and 3d points as inputs and outputs, in contrast to recent work that has used raw images [11,13,24,32,33,45,46,54,56] or 2d probability distributions [33, 56] as inputs, and 3d probabilities [33], 3d motion parameters [54] or basis pose coefficien”
3D Human Pose Estimation = 2D Pose Estimation + Matching (2016, background): “This is classically treated as a constrained optimization problem who’s objective minimizes the 2D reprojection error of an unknown 3D pose and unknown camera [37, 32, 24, 2].”
Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation (2016, background): “feature descriptors [58, 62, 63] and 2D joint locations [2, 3, 5, 20, 36, 51, 57, 69, 70].”
Weakly-supervised Transfer for 3D Human Pose Estimation in the Wild (2017, background): “The first step estimates 2D joint locations [18, 29, 12], and the second step recovers 3D pose from these 2D joints [21, 32, 1].”