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

By Grégory Rogez, Philippe Weinzaepfel, Cordelia Schmid

Citations in the corpus

End-to-End Recovery of Human Shape and Pose (2017, neutral): “Following previous work [36, 33], we down-sample all videos from 50fps to 10fps to reduce redundancy.”
LCR-Net++: Multi-Person 2D and 3D Pose Detection in Natural Images (2018, unknown): “6M to add appearance variations (Figure 8b) and b) poses from the CMU dataset [6] to add variations both in terms of appearance and poses (Figure 8c-d).”
BodyNet: Volumetric Inference of 3D Human Body Shapes (2018, unknown): “We ﬁne-tune our networks which are pre-trained on SURREAL by using sequences from subjects S1, S5, S6, S7, S8, S9 and evaluate on every 64th frame of camera 2 recording subject S11 (i.e., protocol 1 described in [7]).”
A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose (2021, unknown): “While feed-forward estimation of the 3D joint positions [29, 35, 37, 38, 46, 47, 55, 62, 67, 73, 76] or joint angles and bone lengths [56, 77] of the skeleton is highly accurate, such discriminative estimates are prone to misalignment when overlayed onto the input image due to the generalization…”
Video Based Reconstruction of 3D People Models (2018, unknown): “Recent works leverage 2D annotations to train networks for the task of 3D pose estimation [42, 53, 84, 65, 68, 56].”
A Comprehensive Analysis of Deep Regression (2018, unknown): “Regression could also be formulated as classiﬁcation [25], [26].”
Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision (2016, unknown): “Other approaches use the estimated 2D pose to look up a suitable 3D pose from a dictionary [14], or use the ground truth 2D pose based dictionary lookup to create 3D annotations for in-the-wild 2D pose data [53], but neither address the 2D to 3D ambiguity.”
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction (2019, unknown): “There is rich recent literature on 3D pose estimation in the form of a simplistic body skeleton, e.g., [3, 19, 22, 24, 25, 29, 30, 34, 35, 38, 40, 41, 42, 50, 51].”
Learning to Reconstruct People in Clothing From a Single RGB Camera (2019, unknown): “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.”