3D human pose estimation3D人体姿态估计是根据给定的人的图像,产生对应图像具有3d立体空间感的姿态的任务。
CVPR, pp.3090-3099, (2020)
We propose ARCH, a novel end-to-end framework for accurate reconstruction of animation-ready 3D clothed humans from a monocular image
Cited by6BibtexViews62DOI
0
0
CVPR, pp.8926-8936, (2020)
To address the inference over the loopy human structure, our parser relies on a convolutional, message passing based approximation algorithm, which enjoys the advantages of iterative optimization and spatial information preservation
Cited by6BibtexViews110DOI
0
0
CVPR, pp.3276-3285, (2020)
We have presented a novel solution for multi-human 3D pose estimation from multiple camera views
Cited by6BibtexViews25DOI
0
0
CVPR, pp.14412-14420, (2020)
We showed that a proper graph-based spatio-temporal setup for pedestrian trajectory prediction improves over previous methods on several key aspects, including prediction error, computational time and number of parameters
Cited by6BibtexViews34DOI
0
0
CVPR, pp.4262-4271, (2020)
This paper introduces a cascade network architecture for coarse-to-fine Human-object interaction recognition
Cited by4BibtexViews71DOI
0
0
CVPR, pp.11649-11658, (2020)
We show that our proposed model can outperform existing methods on detecting interacting objects, and generalize well to novel objects
Cited by3BibtexViews47DOI
0
0
CVPR, pp.9866-9875, (2020)
This paper proposes steps towards this by inferring a rich representation of hands engaged in interaction method that includes: hand location, side, contact state, and a box around the object in contact
Cited by3BibtexViews25DOI
0
0
CVPR, pp.7363-7373, (2020)
We present TailorNet, a neural model which predicts clothing deformation in 3D as a function of three factors: pose, shape and style, while retaining wrinkle detail
Cited by3BibtexViews31DOI
0
0
CVPR, pp.7202-7211, (2020)
Inspired by, we propose a multiple branches Volumetric Heatmap Autoencoder that takes a set of N volumetric heatmaps H as input
Cited by3BibtexViews42DOI
0
0
CVPR, pp.5030-5040, (2020)
We have introduced the problem of human grasp prediction in RGB images and proposed GanHand, a generative model that 1) estimates the 3D pose of the objects in the scene; 2) predicts grasp types; and 3) refines a 3D hand mesh model
Cited by3BibtexViews37DOI
0
0
CVPR, pp.4989-4999, (2020)
MANO Spectral Spiral GMM Spiral GMM, tune Spiral metrics, we report the F-score at a given threshold d which is the harmonic mean of precision and recall
Cited by3BibtexViews76DOI
0
0
CVPR, pp.7011-7020, (2020)
Though more research is necessary to lower the financial cost and computational complexity of the NLOS imaging system described in this work, we believe that this preliminary work shows the remarkable potential for higher-level reasoning using NLOS imaging in the real-world
Cited by2BibtexViews52DOI
0
0
CVPR, pp.3193-3203, (2020)
The segmentation maps for the hand and object are obtained from a DeepLabV3 network trained on synthetic images of hand and objects
Cited by2BibtexViews79DOI
0
0
CVPR, pp.896-905, (2020)
We propose a deep kinematics analysis framework for monocular 3D pose estimation
Cited by2BibtexViews241DOI
0
0
Maosen Li,Siheng Chen, Yangheng Zhao,Ya Zhang, Yanfeng Wang,Qi Tian
CVPR, pp.211-220, (2020)
We develop multiscale graph computational units to extract features; in the decoder, we develop a graph-based GRU for pose generation
Cited by2BibtexViews98DOI
0
0
CVPR, pp.6151-6161, (2020)
We proposed a self-supervised 3D pose estimation method that disentangles the inherent factors of variations via part guided human image synthesis
Cited by2BibtexViews41DOI
0
0
european conference on computer vision, pp.407-424, (2020)
We have demonstrated that deep learning architectures that integrate combinatorial graph matching solvers perform well on deep graph matching benchmarks
Cited by2BibtexViews24DOI
0
0
CVPR, pp.7021-7032, (2020)
Our experiments show that our non-linear optimization method is accurate enough to compute a training set of clothing images aligned with 3D mesh projections, from which we learn a direct mapping with a neural model
Cited by2BibtexViews37DOI
0
0
Gyeongsik Moon,Kyoung Mu Lee
european conference on computer vision, pp.752-768, (2020)
We propose a I2L-MeshNet, image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image
Cited by1BibtexViews17DOI
0
0
CVPR, pp.7212-7221, (2020)
We have evaluated all components in detail, showing their relevance towards accurate 3d reconstruction of human contact
Cited by1BibtexViews55DOI
0
0