Most of the top-down pose estimation models assume that there exists only one person in a bounding box. However, the assumption is not always correct. In this technical report, we introduce two ideas, instance cue and recurrent refinement, to an existing pose estimator so that the model is able to handle detection boxes with multiple persons properly. When we evaluated our model on the COCO17 keypoints dataset, it showed non-negligible improvement compared to its baseline model. Our model achieved 76.2 mAP as a single model and 77.3 mAP as an ensemble on the test-dev set without additional training data. After additional post-processing with a separate refinement network, our final predictions achieved 77.8 mAP on the COCO test-dev set.
Estimating 3D poses and shapes in the form of meshes from monocular RGB images is challenging. Obviously, it is more difficult than estimating 3D poses only in the form of skeletons or heatmaps. When interacting persons are involved, the 3D mesh reconstruction becomes more challenging due to the ambiguity introduced by person-to-person occlusions. To tackle the challenges, we propose a coarse-to-fine pipeline that benefits from 1) inverse kinematics from the occlusion-robust 3D skeleton estimation and 2) Transformer-based relation-aware refinement techniques. In our pipeline, we first obtain o…
Huazhong University of Science and Technology（华中科技大学）；Peking University（北京大学）；Shanghai Jiao Tong University（上海交通大学）；Megvii Technology（旷视科技）
Person search aims at localizing and identifying a query person from a gallery of uncropped scene images. Different from person re-identification (re-ID), its performance also depends on the localization accuracy of a pedestrian detector. The state-of-the-art methods train the detector individually, and the detected bounding boxes may be sub-optimal for the following re-ID task. To alleviate this issue, we propose a re-ID driven localization refinement framework for providing the refined detection boxes for person search. Specifically, we develop a differentiable ROI transform layer to effecti…
Peking University（北京大学）；Singapore University of Technology and Design（新加坡科技设计大学）；National University of Singapore（新加坡国立大学）；Peng Cheng Laboratory（鹏城实验室）
Unsupervised domain adaptive (UDA) person re-identification (re-ID) is a challenging task due to the missing of labels for the target domain data. To handle this problem, some recent works adopt clustering algorithms to off-line generate pseudo labels, which can then be used as the supervision signal for on-line feature learning in the target domain. However, the off-line generated labels often contain lots of noise that significantly hinders the discriminability of the on-line learned features, and thus limits the final UDA re-ID performance. To this end, we propose a novel approach, called D…
Unsupervised person re-identification (re-ID) aims at learning discriminative representations for person retrieval from unlabeled data. Recent techniques accomplish this task by using pseudo-labels, but these labels are inherently noisy and deteriorate the accuracy. To overcome this problem, several pseudo-label refinement methods have been proposed, but they neglect the fine-grained local context essential for person re-ID. In this paper, we propose a novel Part-based Pseudo Label Refinement (PPLR) framework that reduces the label noise by employing the complementary relationship between glob…
Person attributes are often exploited as mid-level human semantic information to help promote the performance of person re-identification task. In this paper, unlike most existing methods simply taking attribute learning as a classification problem, we perform it in a different way with the motivation that attributes are related to specific local regions, which refers to the perceptual ability of attributes. We utilize the process of attribute detection to generate corresponding attribute-part detectors, whose invariance to many influences like poses and camera views can be guaranteed. With de…
Xidian University（西安电子科技大学）；Zhejiang Lab（之江实验室）；Chongqing University of Posts and Telecommunications（重庆邮电大学）
Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labels, but these pseudo labels are inevitably noisy which deteriorate model performance. In this paper, we propose a Neighbour Consistency guided Pseudo Label Refinement (NCPLR) framework, which can be regarded as a transductive form of label propagation under the assumption that the prediction of each example should be similar to its nearest neighbours'. Specifically, the refined…
Multi-Person Pose Estimation is an interesting yet challenging task in computer vision. In this paper, we conduct a series of refinements with the MSPN and PoseFix Networks, and empirically evaluate their impact on the final model performance through ablation studies. By taking all the refinements, we achieve 78.7 on the COCO test-dev dataset and 76.3 on the COCO test-challenge dataset.
PSDiff: Diffusion Model for Person Search with Iterative and Collaborative Refinement
SGIT AI Lab（SGIT人工智能实验室）；State Grid Shaanxi Electric Power Company Limited, State Grid Corporation of China（中国国家电网有限公司 国网陕西省电力公司）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）
Multi-scale Decomposed Convolution Refinement Network for Visible-Infrared Person Re-Identification
School of Computer Science and Technology, Xinjiang University（新疆大学计算机科学与技术学院）；Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing, Xinjiang University（新疆大学丝绸之路多语言认知计算联合国际研究实验室）
Identity Clue Refinement and Enhancement for Visible-Infrared Person Re-Identification
School of Computer Science, Nanjing University of Information Science and Technology（南京信息工程大学计算机学院）；Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology), Ministry of Education（社会计算与认知智能重点实验室（大连理工大学））；State Key Laboratory of Tibetan Intelligent Information Processing and Application, Qinghai Normal University（藏语智能信息处理与应用国家重点实验室（青海师范大学））
From Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identification
School of Computer Science and Technology, Wuhan University of Science and Technology（武汉科技大学计算机科学与技术学院）；Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan University of Science and Technology（湖北省智能信息处理与实时工业系统重点实验室）；School of Computer Science, Wuhan University（武汉大学计算机学院）；Department of Electrical Engineering and the Institute of Communications Engineering, National Tsing Hua University（清华大学电子工程系和通信工程研究所）；Electronic and Optoelectronic System Research Laboratories, Industrial Technology Research Institute（工业技术研究院电子与光电子系统研究实验室）
Camera-aware Label Refinement for Unsupervised Person Re-identification
Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University（西安交通大学人工智能与机器人研究所）；School of Electronic and Information Engineering, Ningbo University of Technology（宁波工程学院电子与信息工程学院）
Unsupervised Domain Adaptation (UDA) methods for person Re-Identification (Re-ID) rely on target domain samples to model the marginal distribution of the data. To deal with the lack of target domain labels, UDA methods leverage information from labeled source samples and unlabeled target samples. A promising approach relies on the use of unsupervised learning as part of the pipeline, such as clustering methods. The quality of the clusters clearly plays a major role in methods performance, but this point has been overlooked. In this work, we propose a multi-step pseudo-label refinement method t…
We develop a technique for generating smooth and accurate 3D human pose and motion estimates from RGB video sequences. Our method, which we call Motion Estimation via Variational Autoencoder (MEVA), decomposes a temporal sequence of human motion into a smooth motion representation using auto-encoder-based motion compression and a residual representation learned through motion refinement. This two-step encoding of human motion captures human motion in two stages: a general human motion estimation step that captures the coarse overall motion, and a residual estimation that adds back person-speci…
University of California, Berkeley（加州大学伯克利分校）；Carnegie Mellon University（卡内基梅隆大学）；Facebook Reality Labs（Facebook现实实验室）
Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined si…
In multi-person pose estimation, the left/right joint type discrimination is always a hard problem because of the similar appearance. Traditionally, we solve this problem by stacking multiple refinement modules to increase network's receptive fields and capture more global context, which can also increase a great amount of computation. In this paper, we propose a Multi-level Network (MLN) that learns to aggregate features from lower-level (left/right information), upper-level (localization information), joint-limb level (complementary information) and global-level (context) information for dis…
We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a person from a single unconstrained photo. While the input image can be of a smiling person or taken in extreme lighting conditions, our method can reliably produce a high-quality textured model of a person's face in neutral expression and skin textures under diffuse lighting condition. Cutting-edge 3D face reconstruction methods use non-linear morphable face models combined with GAN-based decoders to capture the likeness and details of a person but fail to produce neutral head models with unshaded albed…
KU-Leuven/PSI（比利时鲁汶大学/PSI）；TRACE (Toyota Res in Europe)（TRACE（欧洲丰田研究院））；IMEC（IMEC（微电子研究中心））；Max Planck Institute for Informatics（马克斯·普朗克计算机科学研究所）；Saarland Informatics Campus（萨尔兰信息学园区）；ETH Zurich（苏黎世联邦理工学院）
This paper proposes the novel Pose Guided Person Generation Network (PG$^2$) that allows to synthesize person images in arbitrary poses, based on an image of that person and a novel pose. Our generation framework PG$^2$ utilizes the pose information explicitly and consists of two key stages: pose integration and image refinement. In the first stage the condition image and the target pose are fed into a U-Net-like network to generate an initial but coarse image of the person with the target pose. The second stage then refines the initial and blurry result by training a U-Net-like generator in a…
In this paper, we concern on the bottom-up paradigm in multi-person pose estimation (MPPE). Most previous bottom-up methods try to consider the relation of instances to identify different body parts during the post processing, while ignoring to model the relation among instances or environment in the feature learning process. In addition, most existing works adopt the operations of upsampling and downsampling. During the sampling process, there will be a problem of misalignment with the source features, resulting in deviations in the keypoint features learned by the model. To overcome the abov…
University of Science and Technology of China（中国科学技术大学）；SenseTime Research and Tetras.AI（商汤科技研究院与Tetras.AI）；The University of Hong Kong（香港大学）；The University of Sydney（悉尼大学）
This paper studies the task of estimating the 3D human poses of multiple persons from multiple calibrated camera views. Following the top-down paradigm, we decompose the task into two stages, i.e. person localization and pose estimation. Both stages are processed in coarse-to-fine manners. And we propose three task-specific graph neural networks for effective message passing. For 3D person localization, we first use Multi-view Matching Graph Module (MMG) to learn the cross-view association and recover coarse human proposals. The Center Refinement Graph Module (CRG) further refines the results …
Seoul National University（首尔国立大学）；Kwangwoon University（光云大学）
Multi-person pose estimation from a 2D image is an essential technique for human behavior understanding. In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose. The pose refinement was performed mainly through an end-to-end trainable multi-stage architecture in previous methods. However, they are highly dependent on pose estimation models and require careful model design. By contrast, we propose a model-agnostic pose refinement method. According to a recent study, state-of-the-art 2D human pose estimation methods ha…
Sun Yat-Sen University（中山大学）；ByteDance（字节跳动）；UiT The Arctic University of Norway（挪威北极大学）；Peng Cheng Laboratory（鹏城实验室）
In this paper, we target image-based person-to-person virtual try-on in the presence of diverse poses and large viewpoint variations. Existing methods are restricted in this setting as they estimate garment warping flows mainly based on 2D poses and appearance, which omits the geometric prior of the 3D human body shape. Moreover, current garment warping methods are confined to localized regions, which makes them ineffective in capturing long-range dependencies and results in inferior flows with artifacts. To tackle these issues, we present 3D-aware global correspondences, which are reliable fl…
École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Idiap Research Institute（Idiap研究所）
We propose to leverage recent advances in reliable 2D pose estimation with Convolutional Neural Networks (CNN) to estimate the 3D pose of people from depth images in multi-person Human-Robot Interaction (HRI) scenarios. Our method is based on the observation that using the depth information to obtain 3D lifted points from 2D body landmark detections provides a rough estimate of the true 3D human pose, thus requiring only a refinement step. In that line our contributions are threefold. (i) we propose to perform 3D pose estimation from depth images by decoupling 2D pose estimation and 3D pose re…
University of Science and Technology Beijing（北京科技大学）；Baidu（百度）
Multi-person 3D pose estimation is a challenging task because of occlusion and depth ambiguity, especially in the cases of crowd scenes. To solve these problems, most existing methods explore modeling body context cues by enhancing feature representation with graph neural networks or adding structural constraints. However, these methods are not robust for their single-root formulation that decoding 3D poses from a root node with a pre-defined graph. In this paper, we propose GR-M3D, which models the \textbf{M}ulti-person \textbf{3D} pose estimation with dynamic \textbf{G}raph \textbf{R}easonin…
Max Planck Institute for Informatics（马克斯·普朗克信息研究所）；Saarland Informatics Campus（萨尔州信息学园区）
Multi-person pose estimation in images and videos is an important yet challenging task with many applications. Despite the large improvements in human pose estimation enabled by the development of convolutional neural networks, there still exist a lot of difficult cases where even the state-of-the-art models fail to correctly localize all body joints. This motivates the need for an additional refinement step that addresses these challenging cases and can be easily applied on top of any existing method. In this work, we introduce a pose refinement network (PoseRefiner) which takes as input both…
Beijing University of Posts and Telecommunications（北京邮电大学）；OPPO Research Institute（OPPO研究院）；ByteDance Inc.（字节跳动公司）；Sea AI Lab（Sea人工智能实验室）；Institute of North Electronic Equipment（北方电子设备研究所）；Peng Cheng Laboratory（鹏城实验室）
Multi-person pose estimation generally follows top-down and bottom-up paradigms. Both of them use an extra stage ($\boldsymbol{e.g.,}$ human detection in top-down paradigm or grouping process in bottom-up paradigm) to build the relationship between the human instance and corresponding keypoints, thus leading to the high computation cost and redundant two-stage pipeline. To address the above issue, we propose to represent the human parts as adaptive points and introduce a fine-grained body representation method. The novel body representation is able to sufficiently encode the diverse pose infor…
Beijing University of Posts and Telecommunications（北京邮电大学）；ByteDance Inc.（字节跳动）；Tsinghua University（清华大学）；Horizon Robotics（地平线机器人）
Multi-person pose estimation methods generally follow top-down and bottom-up paradigms, both of which can be considered as two-stage approaches thus leading to the high computation cost and low efficiency. Towards a compact and efficient pipeline for multi-person pose estimation task, in this paper, we propose to represent the human parts as points and present a novel body representation, which leverages an adaptive point set including the human center and seven human-part related points to represent the human instance in a more fine-grained manner. The novel representation is more capable of …
UIUC（伊利诺伊大学厄巴纳-香槟分校）；Microsoft（微软）；University of Oregon（俄勒冈大学）
Bottom-up human pose estimation methods have difficulties in predicting the correct pose for small persons due to challenges in scale variation. In this paper, we present HigherHRNet: a novel bottom-up human pose estimation method for learning scale-aware representations using high-resolution feature pyramids. Equipped with multi-resolution supervision for training and multi-resolution aggregation for inference, the proposed approach is able to solve the scale variation challenge in bottom-up multi-person pose estimation and localize keypoints more precisely, especially for small person. The f…
Facebook AI Research（Facebook人工智能研究）；Tel-Aviv University（特拉维夫大学）
The task of motion transfer between a source dancer and a target person is a special case of the pose transfer problem, in which the target person changes their pose in accordance with the motions of the dancer. In this work, we propose a novel method that can reanimate a single image by arbitrary video sequences, unseen during training. The method combines three networks: (i) a segmentation-mapping network, (ii) a realistic frame-rendering network, and (iii) a face refinement network. By separating this task into three stages, we are able to attain a novel sequence of realistic frames, captur…
