Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userA Synchronized Reprojection-based Model for 3D Human Pose Estimation
126
0
0.0
(
0
)
Added by
Yicheng Deng
Publication date
2021
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
3D human pose estimation is still a challenging problem despite the large amount of work that has been done in this field. Generally, most methods directly use neural networks and ignore certain constraints (e.g., reprojection constraints and joint angle and bone length constraints). This paper proposes a weakly supervised GAN-based model for 3D human pose estimation that considers 3D information along with 2D information simultaneously, in which a reprojection network is employed to learn the mapping of the distribution from 3D poses to 2D poses. In particular, we train the reprojection network and the generative adversarial network synchronously. Furthermore, inspired by the typical kinematic chain space (KCS) matrix, we propose a weighted KCS matrix, which is added into the discriminators input to impose joint angle and bone length constraints. The experimental results on Human3.6M show that our method outperforms state-of-the-art methods by approximately 5.1%.
rate research
Read More
This study considers the 3D human pose estimation problem in a single RGB image by proposing a conditional random field (CRF) model over 2D poses, in which the 3D pose is obtained as a byproduct of the inference process. The unary term of the proposed CRF model is defined based on a powerful heat-map regression network, which has been proposed for 2D human pose estimation. This study also presents a regression network for lifting the 2D pose to 3D pose and proposes the prior term based on the consistency between the estimated 3D pose and the 2D pose. To obtain the approximate solution of the proposed CRF model, the N-best strategy is adopted. The proposed inference algorithm can be viewed as sequential processes of bottom-up generation of 2D and 3D pose proposals from the input 2D image based on deep networks and top-down verification of such proposals by checking their consistencies. To evaluate the proposed method, we use two large-scale datasets: Human3.6M and HumanEva. Experimental results show that the proposed method achieves the state-of-the-art 3D human pose estimation performance.
We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from dynamic observations, recovering plausible pose sequences in the presence of noise and occlusions remains a challenge. For this purpose, we propose an expressive generative model in the form of a conditional variational autoencoder, which learns a distribution of the change in pose at each step of a motion sequence. Furthermore, we introduce a flexible optimization-based approach that leverages HuMoR as a motion prior to robustly estimate plausible pose and shape from ambiguous observations. Through extensive evaluations, we demonstrate that our model generalizes to diverse motions and body shapes after training on a large motion capture dataset, and enables motion reconstruction from multiple input modalities including 3D keypoints and RGB(-D) videos.
In this work, we propose a new solution to 3D human pose estimation in videos. Instead of directly regressing the 3D joint locations, we draw inspiration from the human skeleton anatomy and decompose the task into bone direction prediction and bone length prediction, from which the 3D joint locations can be completely derived. Our motivation is the fact that the bone lengths of a human skeleton remain consistent across time. This promotes us to develop effective techniques to utilize global information across all the frames in a video for high-accuracy bone length prediction. Moreover, for the bone direction prediction network, we propose a fully-convolutional propagating architecture with long skip connections. Essentially, it predicts the directions of different bones hierarchically without using any time-consuming memory units e.g. LSTM). A novel joint shift loss is further introduced to bridge the training of the bone length and bone direction prediction networks. Finally, we employ an implicit attention mechanism to feed the 2D keypoint visibility scores into the model as extra guidance, which significantly mitigates the depth ambiguity in many challenging poses. Our full model outperforms the previous best results on Human3.6M and MPI-INF-3DHP datasets, where comprehensive evaluation validates the effectiveness of our model.
Event camera is an emerging imaging sensor for capturing dynamics of moving objects as events, which motivates our work in estimating 3D human pose and shape from the event signals. Events, on the other hand, have their unique challenges: rather than capturing static body postures, the event signals are best at capturing local motions. This leads us to propose a two-stage deep learning approach, called EventHPE. The first-stage, FlowNet, is trained by unsupervised learning to infer optical flow from events. Both events and optical flow are closely related to human body dynamics, which are fed as input to the ShapeNet in the second stage, to estimate 3D human shapes. To mitigate the discrepancy between image-based flow (optical flow) and shape-based flow (vertices movement of human body shape), a novel flow coherence loss is introduced by exploiting the fact that both flows are originated from the identical human motion. An in-house event-based 3D human dataset is curated that comes with 3D pose and shape annotations, which is by far the largest one to our knowledge. Empirical evaluations on DHP19 dataset and our in-house dataset demonstrate the effectiveness of our approach.
We present Exemplar Fine-Tuning (EFT), a new method to fit a 3D parametric human model to a single RGB input image cropped around a person with 2D keypoint annotations. While existing parametric human model fitting approaches, such as SMPLify, rely on the view-agnostic human pose priors to enforce the output in a plausible 3D pose space, EFT exploits the pose prior that comes from the specific 2D input observations by leveraging a fully-trained 3D pose regressor. We thoroughly compare our EFT with SMPLify, and demonstrate that EFT produces more reliable and accurate 3D human fitting outputs on the same inputs. Especially, we use our EFT to augment a large scale in-the-wild 2D keypoint datasets, such as COCO and MPII, with plausible and convincing 3D pose fitting outputs. We demonstrate that the pseudo ground-truth 3D pose data by EFT can supervise a strong 3D pose estimator that outperforms the previous state-of-the-art in the standard outdoor benchmark (3DPW), even without using any ground-truth 3D human pose datasets such as Human3.6M. Our code and data are available at https://github.com/facebookresearch/eft.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
