Abstract  Description  Claims  Drawing  Search report  Cited references 

Improved techniques for training gans   [0003]  [0054]  [0134] 
Keep it smpl: Automatic estimation of 3d human pose and shape from a single image   [0021]  [0021]  [0027]  [0027]  [0029]  [0134] 
Deep Multitask Architecture for Integrated 2D and 3D Human Sensing   [0021]  [0021]  [0026]  [0134] 
Mask r-cnn   [0021] 
Deeppose: ''Human pose estimation via deep neural networks   [0021]  [0063] 
Efficient simulation of inextensible cloth   [0021] 
Video-based characters: Creating new human performances from a multi-view video database   [0021] 
Adaptive anisotropic remeshing for cloth simulation   [0021] 
Smpl: A skinned multi-person linear model   [0021]  [0134] 
A high performance crf model for clothes parsing   [0021]  [0134] 
Look into person: Self-supervised structure-sensitive learning and a new benchmark for human parsing   [0021]  [0134] 
Deepfashion: Powering robust clothes recognition and retrieval with rich annotations   [0021]  [0134] 
Where to buy it: Matching street clothing photos in online shops   [0021]  [0134] 
Image-to-image translation with conditional adversarial networks   [0021]  [0023]  [0134] 
Photographic image synthesis with cascaded refinement networks   [0021] 
Plug & play generative networks: Conditional iterative generation of images in latent space   [0021]  [0134] 
Photo-realistic single image super-resolution using a generative adversarial network   [0021] 
Unpaired imageto-image translation using cycle-consistent adversarial networks   [0021] 
Photographic image synthesis with cascaded refinement networks   [0021]  [0134] 
High-resolution image inpainting using multi-scale neural patch synthesis   [0021]  [0134] 
Human3.6M: Large Scale Datasets and Predictive Methods for 3D Human Sensing in Natural Environments   [0022]  [0022]  [0134] 
Articulated people detection and pose estimation: Reshaping the future   [0022]  [0134] 
Synthesizing training images for boosting human 3d pose estimation   [0022] 
Multi-view dynamic shape refinement using local temporal integration   [0022]  [0063]  [0134]  [0169] 
ClothCap: ''Seamless 4D clothing capture and retargeting. ACM Transactions on Graphics   [0022] 
Detailed, accurate, human shape estimation from clothed 3d scan sequences   [0022]  [0134] 
A generative model of people in clothing   [0023]  [0023]  [0134] 
Deep convolutional inverse graphics network   [0023]  [0134] 
Generative adversarial nets   [0023] 
Monocular: ''3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints   [0027] 
Smpl: ''A skinned multi-person linear model   [0027] 
Monocular 3D Pose and Shape Estimation of Multiple People in Natural Scenes - The Importance of Multiple Scene Constraints   [0027]  [0134] 
Human parsing with contextualized convolutional neural network   [0041]  [0134] 
Faster r-cnn: ''Towards real-time object detection with region proposal networks   [0053] 
Pose guided person image generation   [0054]  [0054]  [0134] 
Deformable gans for pose-based human image generation   [0054]  [0054]  [0134] 
Faster r-cnn: Towards real-time object detection with region proposal networks   [0055]  [0134] 
Panoptic studio: A massively multiview system for social motion capture   [0061]  [0063]  [0063]  [0093]  [0169] 
Human3.6M: Large scale datasets and predictive methods for 3d human sensing in natural environments   [0061]  [0069]  [0093]  [0169] 
Human appearance transfer   [0061]  [0169] 
Realtime multiperson 2d pose estimation using part affinity fields   [0063] 
DeeperCut: A deeper, stronger, and faster multiperson pose estimation model   [0063] 
Towards accurate multi-person pose estimation in the wild   [0063]  [0169] 
Joint training of a convolutional network and a graphical model for human pose estimation   [0063]  [0169] 
Keep it SMPL: Automatic estimation of 3d human pose and shape from a single image   [0063]  [0063]  [0064]  [0073]  [0077]  [0169] 
SMPL: A skinned multi-person linear model   [0063]  [0063]  [0066]  [0068] 
A simple yet effective baseline for 3d human pose estimation   [0063]  [0169] 
Coarse-to-fine volumetric prediction for single-image 3d human pose   [0063]  [0169] 
Sparseness meets deepness: 3d human pose estimation from monocular video   [0063]  [0169] 
Deep multitask architecture for integrated 2d and 3d human sensing   [0063]  [0063]  [0069]  [0169] 
Mocap-guided data augmentation for 3d pose estimation in the wild   [0063]  [0169] 
Learning to fuse 2d and 3d image cues for monocular body pose estimation   [0063]  [0169] 
Vnect: Realtime 3d human pose estimation with a single rgb camera   [0063]  [0169] 
Surface motion capture transfer with Gaussian process regression   [0063]  [0169] 
Computational Studies of Human Motion: Tracking and Motion Synthesis   [0063]  [0169] 
General automatic human shape and motion capture using volumetric contour cues   [0063]  [0169] 
3d pictorial structures for multiple human pose estimation   [0063]  [0169] 
Marconi-convnet-based marker-less motion capture in outdoor and indoor scenes   [0063]  [0063]  [0169] 
Efficient ConvNet-based marker-less motion capture in general scenes with a low number of cameras   [0063]  [0169] 
Markerless motion capture of multiple characters using Multiview image segmentation   [0063] 
Training deformable models for localization   [0063]  [0169] 
Combined discriminative and generative articulated pose and non-rigid shape estimation   [0063]  [0169] 
Learning joint top-down and bottom-up processes for 3d visual inference   [0063]  [0169] 
Inferring state sequences for non-linear systems with embedded hidden Markov models   [0063]  [0169] 
Reconstructing 3d human pose from 2d image landmarks   [0063]  [0169] 
Ajoint model for 2d and 3d pose estimation from a single image   [0063] 
Variational mixture smoothing for non-linear dynamical systems   [0063]  [0169] 
A dualsource approach for 3d pose estimation from a single image   [0063] 
Estimating Articulated Human Motion with Covariance Scaled Sampling   [0077]  [0169] 
Kinematic jump processes for monocular 3d human tracking   [0078]  [0169] 
On human motion prediction using recurrent neural networks   [0091]  [0169] 
Recurrent network models for human dynamics   [0091]  [0169] 
Gaussian process dynamical models   [0091]  [0169] 
3D Human Sensing, Action and Emotion Recognition in Robot Assisted Therapy of Children with Autism   [0095]  [0169] 
Iterated secondorder label sensitive pooling for 3d human pose estimation   [0095] 
Realtime multi-person 2d pose estimation using part affinity fields   [0134] 
Synthesizing training images for boosting human 3d pose estimation   [0134] 
Efficient simulation of inextensible cloth   [0134] 
Generative adversarial nets   [0134] 
ICCV   [0134] 
Photo-realistic single image super-resolution using a generative adversarial network   [0134] 
Adaptive anisotropic remeshing for cloth simulation   [0134] 
ClothCap: Seamless 4D clothing capture and retargeting   [0134] 
Deeppose: Human pose estimation via deep neural networks   [0134]  [0169] 
Video-based characters: Creating new human performances from a multi-view video database   [0134] 
Unpaired image-to-image translation using cycle-consistent adversarial networks   [0134] 
Realtime multi-person 2d pose estimation using part affinity fields   [0169] 
DeeperCut: A deeper, stronger, and faster multi-person pose estimation model   [0169] 
Iterated second-order label sensitive pooling for 3d human pose estimation   [0169] 
Markerless motion capture of multiple characters using multiview image segmentation   [0169] 
SMPL: A skinned multi-person linear model   [0169] 
A joint model for 2d and 3d pose estimation from a single image   [0169] 
A dual-source approach for 3d pose estimation from a single image   [0169]