Reconstructing multi-human body meshes from a single monocular image is a challenging problem, requiring both individual body meshes and relative 3D positions to produce a coherent scene representation. We introduce MUG (Multi-hUman Graph network), which uses a single graph neural network to construct coherent multi-human meshes from only 2D poses. Our approach demonstrates that pose-based methods can jointly perform depth reasoning and multi-human mesh generation. Existing image-based methods often rely on lab-collected datasets with accurate 3D labels, introducing domain gaps when applied to in-the-wild or art images due to differences in appearance and context. In contrast, MUG leverages the geometric consistency of 2D poses across diverse datasets to mitigate such discrepancies. MUG operates in three phases. First, it constructs a novel heterogeneous graph from multi-human 2D poses, connecting nodes across people and within individuals to capture inter-human interactions and body geometry, including skeletal and mesh structures. Second, a dual-branch graph neural network predicts inter-human depth relations and root-joint-relative mesh coordinates. Finally, these outputs are combined to construct complete multi-human 3D meshes. Despite using only 2D poses and a streamlined architecture, MUG outperforms existing multi-human mesh estimation methods across datasets from diverse domains, including RH, MuPoTS-3D, and 3DPW. Qualitative results show that MUG can handle art images, through-wall scenarios, and poor lighting conditions when paired with advanced 2D pose networks. Both qualitative and quantitative evaluations highlight its generalization ability in open-world scenarios.
We propose a novel framework for accurate 3D human pose estimation in combat sports using sparse multi-camera setups. Our method integrates robust multi-view 2D pose tracking via a transformer-based top-down approach, employing epipolar geometry constraints and long-term video object segmentation for consistent identity tracking across views. Initial 3D poses are obtained through weighted triangulation and spline smoothing, followed by kinematic optimization to refine pose accuracy. We further enhance pose realism and robustness by introducing a multi-person physics-based trajectory optimization step, effectively addressing challenges such as rapid motions, occlusions, and close interactions. Experimental results on diverse datasets, including a new benchmark of elite boxing footage, demonstrate state-of-the-art performance. Additionally, we release comprehensive annotated video datasets to advance future research in multi-person pose estimation for combat sports.
The integration of multi-view imaging and pose estimation represents a significant advance in computer vision applications, offering new possibilities for understanding human movement and interactions. This work presents a new algorithm that improves multi-view multi-person pose estimation, focusing on fast triangulation speeds and good generalization capabilities. The approach extends to whole-body pose estimation, capturing details from facial expressions to finger movements across multiple individuals and viewpoints. Adaptability to different settings is demonstrated through strong performance across unseen datasets and configurations. To support further progress in this field, all of this work is publicly accessible.
We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, i.e., including hands and facial expressions, using the SMPL-X parametric model and 3D location in the camera coordinate system. Our model detects people by predicting coarse 2D heatmaps of person locations, using features produced by a standard Vision Transformer (ViT) backbone. It then predicts their whole-body pose, shape and 3D location using a new cross-attention module called the Human Prediction Head (HPH), with one query attending to the entire set of features for each detected person. As direct prediction of fine-grained hands and facial poses in a single shot, i.e., without relying on explicit crops around body parts, is hard to learn from existing data, we introduce CUFFS, the Close-Up Frames of Full-Body Subjects dataset, containing humans close to the camera with diverse hand poses. We show that incorporating it into the training data further enhances predictions, particularly for hands. Multi-HMR also optionally accounts for camera intrinsics, if available, by encoding camera ray directions for each image token. This simple design achieves strong performance on whole-body and body-only benchmarks simultaneously: a ViT-S backbone on $448{\times}448$ images already yields a fast and competitive model, while larger models and higher resolutions obtain state-of-the-art results.
We address the challenges in estimating 3D human poses from multiple views under occlusion and with limited overlapping views. We approach multi-view, single-person 3D human pose reconstruction as a regression problem and propose a novel encoder-decoder Transformer architecture to estimate 3D poses from multi-view 2D pose sequences. The encoder refines 2D skeleton joints detected across different views and times, fusing multi-view and temporal information through global self-attention. We enhance the encoder by incorporating a geometry-biased attention mechanism, effectively leveraging geometric relationships between views. Additionally, we use detection scores provided by the 2D pose detector to further guide the encoder's attention based on the reliability of the 2D detections. The decoder subsequently regresses the 3D pose sequence from these refined tokens, using pre-defined queries for each joint. To enhance the generalization of our method to unseen scenes and improve resilience to missing joints, we implement strategies including scene centering, synthetic views, and token dropout. We conduct extensive experiments on three benchmark public datasets, Human3.6M, CMU Panoptic and Occlusion-Persons. Our results demonstrate the efficacy of our approach, particularly in occluded scenes and when few views are available, which are traditionally challenging scenarios for triangulation-based methods.
3D pose estimation is an invaluable task in computer vision with various practical applications. Especially, 3D pose estimation for multi-person from a monocular video (3DMPPE) is particularly challenging and is still largely uncharted, far from applying to in-the-wild scenarios yet. We pose three unresolved issues with the existing methods: lack of robustness on unseen views during training, vulnerability to occlusion, and severe jittering in the output. As a remedy, we propose POTR-3D, the first realization of a sequence-to-sequence 2D-to-3D lifting model for 3DMPPE, powered by a novel geometry-aware data augmentation strategy, capable of generating unbounded data with a variety of views while caring about the ground plane and occlusions. Through extensive experiments, we verify that the proposed model and data augmentation robustly generalizes to diverse unseen views, robustly recovers the poses against heavy occlusions, and reliably generates more natural and smoother outputs. The effectiveness of our approach is verified not only by achieving the state-of-the-art performance on public benchmarks, but also by qualitative results on more challenging in-the-wild videos. Demo videos are available at https://www.youtube.com/@potr3d.
Recovering 3D human mesh in the wild is greatly challenging as in-the-wild (ITW) datasets provide only 2D pose ground truths (GTs). Recently, 3D pseudo-GTs have been widely used to train 3D human mesh estimation networks as the 3D pseudo-GTs enable 3D mesh supervision when training the networks on ITW datasets. However, despite the great potential of the 3D pseudo-GTs, there has been no extensive analysis that investigates which factors are important to make more beneficial 3D pseudo-GTs. In this paper, we provide three recipes to obtain highly beneficial 3D pseudo-GTs of ITW datasets. The main challenge is that only 2D-based weak supervision is allowed when obtaining the 3D pseudo-GTs. Each of our three recipes addresses the challenge in each aspect: depth ambiguity, sub-optimality of weak supervision, and implausible articulation. Experimental results show that simply re-training state-of-the-art networks with our new 3D pseudo-GTs elevates their performance to the next level without bells and whistles. The 3D pseudo-GT is publicly available in https://github.com/mks0601/NeuralAnnot_RELEASE.
Although there is a significant development in 3D Multi-view Multi-person Tracking (3D MM-Tracking), current 3D MM-Tracking frameworks are designed separately for footprint and pose tracking. Specifically, frameworks designed for footprint tracking cannot be utilized in 3D pose tracking, because they directly obtain 3D positions on the ground plane with a homography projection, which is inapplicable to 3D poses above the ground. In contrast, frameworks designed for pose tracking generally isolate multi-view and multi-frame associations and may not be robust to footprint tracking, since footprint tracking utilizes fewer key points than pose tracking, which weakens multi-view association cues in a single frame. This study presents a Unified Multi-view Multi-person Tracking framework to bridge the gap between footprint tracking and pose tracking. Without additional modifications, the framework can adopt monocular 2D bounding boxes and 2D poses as the input to produce robust 3D trajectories for multiple persons. Importantly, multi-frame and multi-view information are jointly employed to improve the performance of association and triangulation. The effectiveness of our framework is verified by accomplishing state-of-the-art performance on the Campus and Shelf datasets for 3D pose tracking, and by comparable results on the WILDTRACK and MMPTRACK datasets for 3D footprint tracking.
Depth estimation is usually ill-posed and ambiguous for monocular camera-based 3D multi-person pose estimation. Since LiDAR can capture accurate depth information in long-range scenes, it can benefit both the global localization of individuals and the 3D pose estimation by providing rich geometry features. Motivated by this, we propose a monocular camera and single LiDAR-based method for 3D multi-person pose estimation in large-scale scenes, which is easy to deploy and insensitive to light. Specifically, we design an effective fusion strategy to take advantage of multi-modal input data, including images and point cloud, and make full use of temporal information to guide the network to learn natural and coherent human motions. Without relying on any 3D pose annotations, our method exploits the inherent geometry constraints of point cloud for self-supervision and utilizes 2D keypoints on images for weak supervision. Extensive experiments on public datasets and our newly collected dataset demonstrate the superiority and generalization capability of our proposed method.
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 occlusion-robust 3D skeletons for multiple persons from an RGB image. Then, we apply inverse kinematics to convert the estimated skeletons to deformable 3D mesh parameters. Finally, we apply the Transformer-based mesh refinement that refines the obtained mesh parameters considering intra- and inter-person relations of 3D meshes. Via extensive experiments, we demonstrate the effectiveness of our method, outperforming state-of-the-arts on 3DPW, MuPoTS and AGORA datasets.
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 information and effectively model the relationship between the human instance and corresponding keypoints in a single-forward pass. With the proposed body representation, we further deliver a compact single-stage multi-person pose regression network, termed as AdaptivePose. During inference, our proposed network only needs a single-step decode operation to form the multi-person pose without complex post-processes and refinements. We employ AdaptivePose for both 2D/3D multi-person pose estimation tasks to verify the effectiveness of AdaptivePose. Without any bells and whistles, we achieve the most competitive performance on MS COCO and CrowdPose in terms of accuracy and speed. Furthermore, the outstanding performance on MuCo-3DHP and MuPoTS-3D further demonstrates the effectiveness and generalizability on 3D scenes. Code is available at https://github.com/buptxyb666/AdaptivePose.
Video 3D human pose estimation aims to localize the 3D coordinates of human joints from videos. Recent transformer-based approaches focus on capturing the spatiotemporal information from sequential 2D poses, which cannot model the contextual depth feature effectively since the visual depth features are lost in the step of 2D pose estimation. In this paper, we simplify the paradigm into an end-to-end framework, Instance-guided Video Transformer (IVT), which enables learning spatiotemporal contextual depth information from visual features effectively and predicts 3D poses directly from video frames. In particular, we firstly formulate video frames as a series of instance-guided tokens and each token is in charge of predicting the 3D pose of a human instance. These tokens contain body structure information since they are extracted by the guidance of joint offsets from the human center to the corresponding body joints. Then, these tokens are sent into IVT for learning spatiotemporal contextual depth. In addition, we propose a cross-scale instance-guided attention mechanism to handle the variational scales among multiple persons. Finally, the 3D poses of each person are decoded from instance-guided tokens by coordinate regression. Experiments on three widely-used 3D pose estimation benchmarks show that the proposed IVT achieves state-of-the-art performances.
This work proposes a real-time algorithm for reconstructing 3D human poses in crowded scenes from multiple calibrated views. The key challenge of this problem is to efficiently match 2D observations across multiple views. Previous methods perform multi-view matching either at the full-body level, which is sensitive to 2D pose estimation error, or at the part level, which ignores 2D constraints between different types of body parts in the same view. Instead, our approach reasons about all plausible skeleton proposals during multi-view matching, where each skeleton may consist of an arbitrary number of parts instead of being a whole body or a single part. To this end, we formulate the multi-view matching problem as mode seeking in the space of skeleton proposals and develop an efficient algorithm named QuickPose to solve the problem, which enables real-time motion capture in crowded scenes. Experiments show that the proposed algorithm achieves the state-of-the-art performance in terms of both speed and accuracy on public datasets.
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}easoning. The decoding graph in GR-M3D is predicted instead of pre-defined. In particular, It firstly generates several data maps and enhances them with a scale and depth aware refinement module (SDAR). Then multiple root keypoints and dense decoding paths for each person are estimated from these data maps. Based on them, dynamic decoding graphs are built by assigning path weights to the decoding paths, while the path weights are inferred from those enhanced data maps. And this process is named dynamic graph reasoning (DGR). Finally, the 3D poses are decoded according to dynamic decoding graphs for each detected person. GR-M3D can adjust the structure of the decoding graph implicitly by adopting soft path weights according to input data, which makes the decoding graphs be adaptive to different input persons to the best extent and more capable of handling occlusion and depth ambiguity than previous methods. We empirically show that the proposed bottom-up approach even outperforms top-down methods and achieves state-of-the-art results on three 3D pose datasets.
While the voxel-based methods have achieved promising results for multi-person 3D pose estimation from multi-cameras, they suffer from heavy computation burdens, especially for large scenes. We present Faster VoxelPose to address the challenge by re-projecting the feature volume to the three two-dimensional coordinate planes and estimating X, Y, Z coordinates from them separately. To that end, we first localize each person by a 3D bounding box by estimating a 2D box and its height based on the volume features projected to the xy-plane and z-axis, respectively. Then for each person, we estimate partial joint coordinates from the three coordinate planes separately which are then fused to obtain the final 3D pose. The method is free from costly 3D-CNNs and improves the speed of VoxelPose by ten times and meanwhile achieves competitive accuracy as the state-of-the-art methods, proving its potential in real-time applications.
While monocular 3D pose estimation seems to have achieved very accurate results on the public datasets, their generalization ability is largely overlooked. In this work, we perform a systematic evaluation of the existing methods and find that they get notably larger errors when tested on different cameras, human poses and appearance. To address the problem, we introduce VirtualPose, a two-stage learning framework to exploit the hidden "free lunch" specific to this task, i.e. generating infinite number of poses and cameras for training models at no cost. To that end, the first stage transforms images to abstract geometry representations (AGR), and then the second maps them to 3D poses. It addresses the generalization issue from two aspects: (1) the first stage can be trained on diverse 2D datasets to reduce the risk of over-fitting to limited appearance; (2) the second stage can be trained on diverse AGR synthesized from a large number of virtual cameras and poses. It outperforms the SOTA methods without using any paired images and 3D poses from the benchmarks, which paves the way for practical applications. Code is available at https://github.com/wkom/VirtualPose.
Inter-person occlusion and depth ambiguity make estimating the 3D poses of monocular multiple persons as camera-centric coordinates a challenging problem. Typical top-down frameworks suffer from high computational redundancy with an additional detection stage. By contrast, the bottom-up methods enjoy low computational costs as they are less affected by the number of humans. However, most existing bottom-up methods treat camera-centric 3D human pose estimation as two unrelated subtasks: 2.5D pose estimation and camera-centric depth estimation. In this paper, we propose a unified model that leverages the mutual benefits of both these subtasks. Within the framework, a robust structured 2.5D pose estimation is designed to recognize inter-person occlusion based on depth relationships. Additionally, we develop an end-to-end geometry-aware depth reasoning method that exploits the mutual benefits of both 2.5D pose and camera-centric root depths. This method first uses 2.5D pose and geometry information to infer camera-centric root depths in a forward pass, and then exploits the root depths to further improve representation learning of 2.5D pose estimation in a backward pass. Further, we designed an adaptive fusion scheme that leverages both visual perception and body geometry to alleviate inherent depth ambiguity issues. Extensive experiments demonstrate the superiority of our proposed model over a wide range of bottom-up methods. Our accuracy is even competitive with top-down counterparts. Notably, our model runs much faster than existing bottom-up and top-down methods.
This paper presents Volumetric Transformer Pose estimator (VTP), the first 3D volumetric transformer framework for multi-view multi-person 3D human pose estimation. VTP aggregates features from 2D keypoints in all camera views and directly learns the spatial relationships in the 3D voxel space in an end-to-end fashion. The aggregated 3D features are passed through 3D convolutions before being flattened into sequential embeddings and fed into a transformer. A residual structure is designed to further improve the performance. In addition, the sparse Sinkhorn attention is empowered to reduce the memory cost, which is a major bottleneck for volumetric representations, while also achieving excellent performance. The output of the transformer is again concatenated with 3D convolutional features by a residual design. The proposed VTP framework integrates the high performance of the transformer with volumetric representations, which can be used as a good alternative to the convolutional backbones. Experiments on the Shelf, Campus and CMU Panoptic benchmarks show promising results in terms of both Mean Per Joint Position Error (MPJPE) and Percentage of Correctly estimated Parts (PCP). Our code will be available.
Monocular 3D human pose estimation has made progress in recent years. Most of the methods focus on single persons, which estimate the poses in the person-centric coordinates, i.e., the coordinates based on the center of the target person. Hence, these methods are inapplicable for multi-person 3D pose estimation, where the absolute coordinates (e.g., the camera coordinates) are required. Moreover, multi-person pose estimation is more challenging than single pose estimation, due to inter-person occlusion and close human interactions. Existing top-down multi-person methods rely on human detection (i.e., top-down approach), and thus suffer from the detection errors and cannot produce reliable pose estimation in multi-person scenes. Meanwhile, existing bottom-up methods that do not use human detection are not affected by detection errors, but since they process all persons in a scene at once, they are prone to errors, particularly for persons in small scales. To address all these challenges, we propose the integration of top-down and bottom-up approaches to exploit their strengths. Our top-down network estimates human joints from all persons instead of one in an image patch, making it robust to possible erroneous bounding boxes. Our bottom-up network incorporates human-detection based normalized heatmaps, allowing the network to be more robust in handling scale variations. Finally, the estimated 3D poses from the top-down and bottom-up networks are fed into our integration network for final 3D poses. To address the common gaps between training and testing data, we do optimization during the test time, by refining the estimated 3D human poses using high-order temporal constraint, re-projection loss, and bone length regularizations. Our evaluations demonstrate the effectiveness of the proposed method. Code and models are available: https://github.com/3dpose/3D-Multi-Person-Pose.
The recovery of multi-person 3D poses from a single RGB image is a severely ill-conditioned problem due to the inherent 2D-3D depth ambiguity, inter-person occlusions, and body truncations. To tackle these issues, recent works have shown promising results by simultaneously reasoning for different people. However, in most cases this is done by only considering pairwise person interactions, hindering thus a holistic scene representation able to capture long-range interactions. This is addressed by approaches that jointly process all people in the scene, although they require defining one of the individuals as a reference and a pre-defined person ordering, being sensitive to this choice. In this paper, we overcome both these limitations, and we propose an approach for multi-person 3D pose estimation that captures long-range interactions independently of the input order. For this purpose, we build a residual-like permutation-invariant network that successfully refines potentially corrupted initial 3D poses estimated by an off-the-shelf detector. The residual function is learned via Set Transformer blocks, that model the interactions among all initial poses, no matter their ordering or number. A thorough evaluation demonstrates that our approach is able to boost the performance of the initially estimated 3D poses by large margins, achieving state-of-the-art results on standardized benchmarks. Additionally, the proposed module works in a computationally efficient manner and can be potentially used as a drop-in complement for any 3D pose detector in multi-people scenes.