LCR-Net: Localization-Classification-Regression for Human Pose

By Grégory Rogez, Philippe Weinzaepfel, Cordelia Schmid. 2017

324 citations recorded by the source corpus.

Subfields: Biomedical Engineering, 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 Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

2D/3D Pose Estimation and Action Recognition Using Multitask Deep Learning (2018, neutral): “2 Regression methods LCR-Net [42] 2017 – – 74.”
End-to-End Recovery of Human Shape and Pose (2017, methodology): “Following previous work [33, 36], we downsample all videos from 50fps to 10fps to”
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image (2020, methodology): “[33] achieved significantly better 3D multi-person pose estimation accuracy using 3D heatmap compared with previous coordinate regression-based methods [41].”
Ordinal Depth Supervision for 3D Human Pose Estimation (2018, methodology): “Prior work uses ConvNets to regress the coordinates of the 3D joints [22, 47, 48, 51, 44, 26], to regress 3D heatmaps [32], or to classify each image in the appropriate pose class [39, 40].”
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images (2018, methodology): “One of the conclusions in the earlier version of this work [14] was that LCR-Net”
Self-Supervised Learning of 3D Human Pose Using Multi-View Geometry (2019, methodology): “Our self supervised (SS) model performs quite well compared to the recent fully 3D supervised methods [29, 32, 33, 40] which require abundant labeled data to learn.”
Sim2real transfer learning for 3D human pose estimation: motion to the rescue (2019, background): “Other works regress poses directly from pixels [46, 55, 56, 68, 71, 77, 78, 96], which generally relies on having a good match between training and testing.”
Monocular human pose estimation: A survey of deep learning-based methods (2020, methodology): “…et al., 2017c; Rhodin et al., 2018a) (3) Other model-based : probabilistic model (Tome et al., 2017) 3D Multiple bottom-up (Mehta et al., 2017b), top-down (Rogez et al., 2017), SMPL-based (Zanﬁr et al., 2018), real-time (Mehta et al., 2019) cations in the 2D surface, then extend them to 3D space.”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, background): “Using only a single image, available human parsing studies have covered popular topics starting from 2D pose detection [41, 6, 39], advancing to 3D pose detection [33, 44, 64], and finally expanding to body shape capture [27] using a human statistic template such as SMPL [32].”
HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation (2020, background): “Single-stage approaches [51, 56, 36, 76, 38, 63, 39, 71] directly estimate the 3D joint locations from the input image.”
Learning to Reconstruct People in Clothing From a Single RGB Camera (2019, background): “Recent pure bottom-up approaches to human analysis [50, 49, 58, 87, 69, 71, 62] typically predict shape represented as a coarse stick figure or bone skeleton, and can not estimate body shape or clothing.”
Human Pose Regression with Residual Log-likelihood Estimation (2021, background): “[50, 51] classify the human pose into a set of K anchor-poses and a regression module is proposed to refine the anchor to the final prediction.”
Learning to Estimate 3D Human Pose and Shape from a Single Color Image (2018, background): “Many recent works follow the end-to-end paradigm [48, 40, 42, 46, 55], using images as input to predict 3D joint locations [23, 45, 34, 28], regress 3D heatmaps [31], or classify the image in a particular pose class [39, 40].”
Human Pose Regression by Combining Indirect Part Detection and Contextual Information (2017, methodology): “Moreover, regression based methods are conceptually more adapted to 2D and 3D scenarios and can be used in-distinctly on both cases [36, 38].”
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision (2016, methodology): “Other approaches use the estimated 2D pose to look up a suitable 3D pose from a dictionary [12], or use the ground truth 2D pose based dictionary lookup to create 3D annotations for in-the-wild 2D pose data [48], but neither address the 2D to 3D ambiguity.”