Objects manipulated by the hand (i.e., manipulanda) are particularly challenging to reconstruct from Internet videos. Not only does the hand occlude much of the object, but also the object is often only visible in a small number of image pixels. At the same time, two strong anchors emerge in this setting: (1) estimated 3D hands help disambiguate the location and scale of the object, and (2) the set of manipulanda is small relative to all possible objects. With these insights in mind, we present a scalable paradigm for hand-held object reconstruction that builds on recent breakthroughs in large language/vision models and 3D object datasets. Given a monocular RGB video, we aim to reconstruct hand-held object geometry in 3D, over time. In order to obtain the best performing single frame model, we first present MCC-Hand-Object (MCCHO), which jointly reconstructs hand and object geometry given a single RGB image and inferred 3D hand as inputs. Subsequently, we prompt a text-to-3D generative model using a VLM to retrieve a 3D object model that matches the object in the image(s); we call this alignment Retrieval-Augmented Reconstruction (RAR). RAR provides unified object geometry across all frames, and the result is rigidly aligned with both the input images and 3D MCCHO observations in a temporally consistent manner. Experiments demonstrate that our approach achieves state-of-theart performance on lab and Internet image/video datasets. We make our code and models available on the project website: https://janehwu.github.io/mcc-ho

We revisit the role of texture in monocular 3D hand reconstruction, not as an afterthought for photorealism, but as a dense, spatially grounded cue that can actively support pose and shape estimation. Our observation is simple: even in high-performing models, the overlay between predicted hand geometry and image appearance is often imperfect, suggesting that texture alignment may be an underused supervisory signal. We propose a lightweight texture module that embeds per-pixel observations into UV texture space and enables a novel dense alignment loss between predicted and observed hand appearances. Our approach assumes access to a differentiable rendering pipeline and a model that maps images to 3D hand meshes with known topology, allowing us to back-project a textured hand onto the image and perform pixel-based alignment. The module is self-contained and easily pluggable into existing reconstruction pipelines. To isolate and highlight the value of texture-guided supervision, we augment HaMeR [47], a high-performing yet unadorned transformer architecture for 3D hand pose estimation. The resulting system improves both accuracy and realism, demonstrating the value of appearance-guided alignment in hand reconstruction. Code, models and weights are available at https://gkarv.github.io/hand-texture-module

Feedback is essential for learning a new skill or improving one's current skill-level. However, current methods for skill-assessment from video only provide scores or compare demonstrations, leaving the burden of knowing what to do differently on the user. We introduce a novel method to generate actionable feedback (AF) from video of a person doing a physical activity, such as basketball or soccer. Our method takes a video demonstration and its accompanying 3D body pose and generates (1) free-form expert commentary describing what the person is doing well and what they could improve, and (2) a visual expert demonstration that incorporates the required corrections. We show how to leverage Ego-Exo4D's [29] videos of skilled activity and expert commentary together with a strong language model to create a weakly-supervised training dataset for this task, and we devise a multimodal video-language model to infer coaching feedback. Our method is able to reason across multi-modal input combinations to output full-spectrum, actionable coaching—expert commentary, expert video retrieval, and expert pose generation—outperforming strong vision-language models on both established metrics and human preference studies.

Anticipating how a person will interact with objects in an environment is essential for activity understanding, but existing methods are limited to the 2D space of video frames—capturing physically ungrounded predictions of "what" and ignoring the "where" and "how". We introduce FICTION for 4D future interaction prediction from videos. Given an input video of a human activity, the goal is to predict which objects at what 3D locations the person will interact with in the next time period (e.g., cabinet, fridge), and how they will execute that interaction (e.g., poses for bending, reaching, pulling). Our novel model FIction fuses the past video observation of the person’s actions and their environment to predict both the "where" and "how" of future interactions. Through comprehensive experiments on a variety of activities and real-world environments in Ego-Exo4D, we show that our proposed approach outperforms prior autoregressive and (lifted) 2D video models substantially, with more than 30% relative gains.

We propose scaling up 3D scene reconstruction by training with synthesized data. At the core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K scenes—over 50 times larger than the prior real dataset DL3DV—dramatically scaling the training data. To enable scalable data generation, our key idea is eliminating semantic information, removing the need to model complex semantic priors such as object affordances and scene composition. Instead, we model scenes with basic spatial structures and geometry primitives, offering scalability. Besides, we control data complexity to facilitate training while loosely aligning it with real-world data distribution to benefit real-world generalization. We explore training LRMs with both MegaSynth and available real data. Experiment results show that joint training or pre-training with MegaSynth improves reconstruction quality by 1.2 to 1.8 dB PSNR across diverse image domains. Moreover, models trained solely on MegaSynth perform comparably to those trained on real data, underscoring the low-level nature of 3D reconstruction. Additionally, we provide an in-depth analysis of MegaSynth’s properties for enhancing model capability, training stability, and generalization, as well as application to other tasks.

In this paper, we introduce a method for reconstructing 3D humans from a single image using a biomechanically accurate skeleton model. To achieve this, we train a transformer that takes an image as input and estimates the parameters of the model. Due to the lack of training data for this task, we build a pipeline to produce pseudo ground truth model parameters for single images and implement a training procedure that iteratively refines these pseudo labels. Compared to state-of-the-art methods for 3D human mesh recovery, our model achieves competitive performance on standard benchmarks, while it significantly outperforms them in settings with extreme 3D poses and viewpoints. Additionally, we show that previous reconstruction methods frequently violate joint angle limits, leading to unnatural rotations. In contrast, our approach leverages the biomechanically plausible degrees of freedom making more realistic joint rotation estimates. We validate our approach across multiple human pose estimation benchmarks. We make the code, models and data available at: https://isshikihugh.github.io/HSMR/

We present EgoAllo, a system for human motion estimation from a head-mounted device. Using only egocentric SLAM poses and images, EgoAllo guides sampling from a conditional diffusion model to estimate 3D body pose, height, and hand parameters that capture a device wearer's actions in the allocentric coordinate frame of the scene. To achieve this, our key insight is in representation: we propose spatial and temporal invariance criteria for improving model performance, from which we derive a head motion conditioning parameterization that improves estimation by up to 18%. We also show how the bodies estimated by our system can improve hand estimation: the resulting kinematic and temporal constraints can reduce world-frame errors in single-frame estimates by 40%.

Using the latent diffusion model has proven effective in developing novel 3D generation techniques. To harness the latent diffusion model, a key challenge is designing a high-fidelity and efficient representation that links the latent space and the 3D space. In this paper, we introduce Atlas Gaussians, a novel representation for feed-forward native 3D generation. Atlas Gaussians represent a shape as the union of local patches, and each patch can decode 3D Gaussians. We parameterize a patch as a sequence of feature vectors and design a learnable function to decode 3D Gaussians from the feature vectors. In this process, we incorporate UV-based sampling, enabling the generation of a sufficiently large, and theoretically infinite, number of 3D Gaussian points. The large amount of 3D Gaussians enables the generation of high-quality details. Moreover, due to local awareness of the representation, the transformer-based decoding procedure operates on a patch level, ensuring efficiency. We train a variational autoencoder to learn the Atlas Gaussians representation, and then apply a latent diffusion model on its latent space for learning 3D Generation. Experiments show that our approach outperforms the prior arts of feed-forward native 3D generation. Project page: https://yanghtr.github.io/projects/atlas_gaussians.

We introduce Gaussian Articulated Template Model (GART), an explicit, efficient, and expressive representation for non-rigid articulated subject capturing and rendering from monocular videos. GART utilizes a mixture of moving 3D Gaussians to explicitly approximate a deformable subject's geometry and appearance. It takes advantage of a categorical template model prior (SMPL, SMAL, etc.) with learnable forward skinning while further generalizing to more complex non-rigid deformations with novel latent bones. GART can be reconstructed via differentiable rendering from monocular videos in seconds or minutes and rendered in novel poses faster than 150fps.

Social interaction is a fundamental aspect of human behavior and communication. The way individuals position themselves in relation to others, also known as proxemics, conveys social cues and affects the dynamics of social interaction. Reconstructing such interaction from images presents challenges because of mutual occlusion and the limited availability of large training datasets. To address this, we present a novel approach that learns a prior over the 3D proxemics two people in close social interaction and demonstrate its use for single-view 3D reconstruction. We start by creating 3D training data of interacting people using image datasets with contact annotations. We then model the proxemics using a novel denoising diffusion model called BUDDI that learns the joint distribution over the poses of two people in close social interaction. Sampling from our generative proxemics model produces realistic 3D human interactions, which we validate through a perceptual study. We use BUDDI in reconstructing two people in close proximity from an image without any contact annotation via an optimization approach that uses the diffusion model as a prior. Our approach recovers accurate 3D social interactions from noisy initial estimates, outperforming state-of-the-art methods. Our code, data, and model are available at: muelea. github.io/buddi.

We present an approach that can reconstruct hands in 3D from monocular input. Our approach for Hand Mesh Recovery, HaMeR, follows a fully transformer-based architecture and can analyze hands with significantly increased accuracy and robustness compared to previous work. The key to HaMeR's success lies in scaling up both the data used for training and the capacity of the deep network for hand reconstruction. For training data, we combine multiple datasets that contain 2D or 3D hand annotations. For the deep model, we use a large scale Vision Transformer architecture. Our final model consistently outperforms the previous baselines on popular 3D hand pose benchmarks. To further evaluate the effect of our design in non-controlled settings, we annotate existing in-the-wild datasets with 2D hand keypoint annotations. On this newly collected dataset of annotations, HInt, we demonstrate significant improvements over existing baselines. We will make our code, data and models publicly available upon publication. We make our code, data and models available on the project website: https://geopavlakos.github.io/hamer/. “It is because of his being armed with hands that man is the most intelligent animal.” Anaxagoras

We introduce MultiPhys, a method designed for recovering multi-person motion from monocular videos. Our focus lies in capturing coherent spatial placement between pairs of individuals across varying degrees of engagement. MultiPhys, being physically aware, exhibits robustness to jittering and occlusions, and effectively eliminates penetration issues between the two individuals. We devise a pipeline in which the motion estimated by a kinematic-based method is fed into a physics simulator in an autoregressive manner. We introduce distinct components that enable our model to harness the simulator's properties without compromising the accuracy of the kinematic estimates. This results in final motion estimates that are both kinematically coherent and physically compliant. Extensive evaluations on three challenging datasets characterized by substantial inter-person interaction show that our method significantly reduces errors associated with penetration and foot skating, while performing competitively with the state-of-the-art on motion accuracy and smoothness. Results and code can be found in our project page.

Nuanced expressiveness, especially through detailed hand and facial expressions, is pivotal for enhancing the realism and vitality of digital human representations. In this work, we aim to learn expressive human avatars from a monocular RGB video; a setting that introduces new challenges in capturing and animating fine-grained details. To this end, we introduce EVA, a drivable human model that can recover fine details based on 3D Gaussians and an expressive parametric human model, SMPL-X. Focused on enhancing expressiveness, our work makes three key contributions. First, we highlight the importance of aligning the SMPL-X model with the video frames for effective avatar learning. Recognizing the limitations of current methods for estimating SMPL-X parameters from in-the-wild videos, we introduce a reconstruction module that significantly improves the image-model alignment. Second, we propose a context-aware adaptive density control strategy, which is adaptively adjusting the gradient thresholds to accommodate the varied granularity across body parts. Third, we develop a feedback mechanism that predicts per-pixel confidence to better guide the optimization of 3D Gaussians. Extensive experiments on two benchmarks demonstrate the superiority of our approach both quantitatively and qualitatively, especially on the fine-grained hand and facial details. We make our code available at the project website: https://evahuman.github.io.

This paper introduces CoFie, a novel local geometry-aware neural surface representation. CoFie is motivated by the theoretical analysis of local SDFs with quadratic approximation. We find that local shapes are highly compressive in an aligned coordinate frame defined by the normal and tangent directions of local shapes. Accordingly, we introduce Coordinate Field, which is a composition of coordinate frames of all local shapes. The Coordinate Field is optimizable and is used to transform the local shapes from the world coordinate frame to the aligned shape coordinate frame. It largely reduces the complexity of local shapes and benefits the learning of MLP-based implicit representations. Moreover, we introduce quadratic layers into the MLP to enhance expressiveness concerning local shape geometry. CoFie is a generalizable surface representation. It is trained on a curated set of 3D shapes and works on novel shape instances during testing. When using the same amount of parameters with prior works, CoFie reduces the shape error by 48% and 56% on novel instances of both training and unseen shape categories. Moreover, CoFie demonstrates comparable performance to prior works when using even 70% fewer parameters. Code and model can be found here: https://hwjiang1510.github.io/CoFie/

In this work we study the benefits of using tracking and 3D poses for action recognition. To achieve this, we take the Lagrangian view on analysing actions over a trajectory of human motion rather than at a fixed point in space. Taking this stand allows us to use the tracklets of people to predict their actions. In this spirit, first we show the benefits of using 3D pose to infer actions, and study person-person in-teractions. Subsequently, we propose a Lagrangian Action Recognition model by fusing 3D pose and contextualized appearance over tracklets. To this end, our method achieves state-of-the-art performance on the AVA v2.2 dataset on both pose only settings and on standard benchmark settings. When reasoning about the action using only pose cues, our pose model achieves +10.0 mAP gain over the corresponding state-of-the-art while our fused model has a gain of +2.8 mAP over the best state-of-the-art model. Code and results are available at: https://brjathu.github.io/LART

This paper shows that it is possible to learn models for monocular 3D reconstruction of articulated objects (e.g. horses, cows, sheep), using as few as 50–150 images labeled with 2D keypoints. Our proposed approach involves training category-specific keypoint estimators, generating 2D keypoint pseudo-labels on unlabeled web images, and using both the labeled and self-labeled sets to train 3D reconstruction models. It is based on two key insights: (1) 2D keypoint estimation networks trained on as few as 50– 150 images of a given object category generalize well and generate reliable pseudo-labels; (2) a data selection mechanism can automatically create a “curated” subset of the unlabeled web images that can be used for training - we evaluate four data selection methods. Coupling these two insights enables us to train models that effectively utilize web images, resulting in improved 3D reconstruction performance for several articulated object categories beyond the fully-supervised baseline. Our approach can quickly bootstrap a model and requires only a few images labeled with 2D keypoints. This requirement can be easily satisfied for any new object category. To showcase the practicality of our approach for predicting the 3D shape of arbitrary object categories, we annotate 2D keypoints on 250 giraffe and bear images from COCO in just 2.5 hours per category.

We propose a method to reconstruct global human trajectories from videos in the wild. Our optimization method decouples the camera and human motion, which allows us to place people in the same world coordinate frame. Most existing methods do not model the camera motion; methods that rely on the background pixels to infer 3D human motion usually require a full scene reconstruction, which is often not possible for in-the-wild videos. However, even when existing SLAM systems cannot recover accurate scene reconstructions, the background pixel motion still provides enough signal to constrain the camera motion. We show that relative camera estimates along with data-driven human motion priors can resolve the scene scale ambiguity and recover global human trajectories. Our method robustly recovers the global 3D trajectories of people in challenging in-the-wild videos, such as PoseTrack. We quantify our improvement over existing methods on 3D human dataset Egobody. We further demonstrate that our recovered camera scale allows us to reason about motion of multiple people in a shared coordinate frame, which improves performance of downstream tracking in PoseTrack.

We present an approach to reconstruct humans and track them over time. At the core of our approach, we propose a fully "transformerized" version of a network for human mesh recovery. This network, HMR 2.0, advances the state of the art and shows the capability to analyze unusual poses that have in the past been difficult to reconstruct from single images. To analyze video, we use 3D reconstructions from HMR 2.0 as input to a tracking system that operates in 3D. This enables us to deal with multiple people and maintain identities through occlusion events. Our complete approach, 4DHumans, achieves state-of-the-art results for tracking people from monocular video. Furthermore, we demonstrate the effectiveness of HMR 2.0 on the downstream task of action recognition, achieving significant improvements over previous pose-based action recognition approaches. Our code and models are available on the project website: https://shubham-goel.github.io/4dhumans/.

Videos from edited media like movies are a useful, yet underexplored source of information, with rich variety of appearance and interactions between humans depicted over a large temporal context. However, the richness of data comes at the expense of fundamental challenges such as abrupt shot changes and close up shots of actors with heavy truncation, which limits the applicability of existing 3D human understanding methods. In this paper, we address these limitations with the insight that while shot changes of the same scene incur a discontinuity between frames, the 3D structure of the scene still changes smoothly. This allows us to handle frames before and after the shot change as multi-view signal that provide strong cues to recover the 3D state of the actors. We propose a multi-shot optimization framework that realizes this insight, leading to improved 3D reconstruction and mining of sequences with pseudo-ground truth 3D human mesh. We treat this data as valuable supervision for models that enable human mesh recovery from movies; both from single image and from video, where we propose a transformer-based temporal encoder that can naturally handle missing observations due to shot changes in the input frames. We demonstrate the importance of our insight and proposed models through extensive experiments. The tools we develop open the door to processing and analyzing in 3D content from a large library of edited media, which could be helpful for many downstream applications. Code, models and data are available at: https://geopavlakos.github.io/multishot/.

We present an approach for tracking people in monocular videos by predicting their future 3D representations. To achieve this, we first lift people to 3D from a single frame in a robust manner. This lifting includes information about the 3D pose of the person, their location in the 3D space, and the 3D appearance. As we track a person, we collect 3D observations over time in a tracklet representation. Given the 3D nature of our observations, we build temporal models for each one of the previous attributes. We use these models to predict the future state of the tracklet, including 3D appearance, 3D location, and 3D pose. For a future frame, we compute the similarity between the predicted state of a tracklet and the single frame observations in a probabilistic manner. Association is solved with simple Hungarian matching, and the matches are used to update the respective tracklets. We evaluate our approach on various benchmarks and report state-of-the-art results. Code and models are available at: https://brjathu.github.io/PHALP.

We address the challenging problem of continuous sign language recognition (CSLR) from RGB videos, proposing a novel deep-learning framework that employs spatio-temporal graph convolutional networks (ST-GCNs), which operate on multiple, appropriately fused feature streams, capturing the signer’s pose, shape, appearance, and motion information. In addition to introducing such networks to the continuous recognition problem, our model’s novelty lies on: (i) the feature streams considered and their blending into three ST-GCN modules; (ii) the combination of such modules with bi-directional long short-term memory networks, thus capturing both short-term embedded signing dynamics and long-range feature dependencies; and (iii) the fusion scheme, where the resulting modules operate in parallel, their posteriors aligned via a guiding connectionist temporal classification method, and fused for sign gloss prediction. Notably, concerning (i), in addition to traditional CSLR features, we investigate the utility of 3D human pose and shape parameterization via the "ExPose" approach, as well as 3D skeletal joint information that is regressed from detected 2D joints. We evaluate the proposed system on two well-known CSLR benchmarks, conducting extensive ablations on its modules. We achieve the new state-of-the-art on one of the two datasets, while reaching very competitive performance on the other.

Independent Sign Language Recognition is a complex visual recognition problem that combines several challenging tasks of Computer Vision due to the necessity to exploit and fuse information from hand gestures, body features and facial expressions. While many state-of-the-art works have managed to deeply elaborate on these features independently, to the best of our knowledge, no work has adequately combined all three information channels to efficiently recognize Sign Language. In this work, we employ SMPL-X, a contemporary parametric model that enables joint extraction of 3D body shape, face and hands information from a single image. We use this holistic 3D reconstruction for SLR, demonstrating that it leads to higher accuracy than recognition from raw RGB images and their optical flow fed into the state-of-the-art I3D-type network for 3D action recognition and from 2D Openpose skeletons fed into a Recurrent Neural Network. Finally, a set of experiments on the body, face and hand features showed that neglecting any of these, significantly reduces the classification accuracy, proving the importance of jointly modeling body shape, facial expression and hand pose for Sign Language Recognition.

This paper focuses on the problem of 3D human reconstruction from 2D evidence. Although this is an inherently ambiguous problem, the majority of recent works avoid the uncertainty modeling and typically regress a single estimate for a given input. In contrast to that, in this work, we propose to embrace the reconstruction ambiguity and we recast the problem as learning a mapping from the input to a distribution of plausible 3D poses. Our approach is based on the normalizing flows model and offers a series of advantages. For conventional applications, where a single 3D estimate is required, our formulation allows for efficient mode computation. Using the mode leads to performance that is comparable with the state of the art among deterministic unimodal regression models. Simultaneously, since we have access to the likelihood of each sample, we demonstrate that our model is useful in a series of downstream tasks, where we leverage the probabilistic nature of the prediction as a tool for more accurate estimation. These tasks include reconstruction from multiple uncalibrated views, as well as human model fitting, where our model acts as a powerful image-based prior for mesh recovery. Our results validate the importance of probabilistic modeling, and indicate state-of-the-art performance across a variety of settings. Code and models are available at: https://www.seas.upenn.edu/~nkolot/projects/prohmr.

We present a novel approach for tracking multiple people in video. Unlike past approaches which employ 2D representations, we focus on using 3D representations of people, located in three-dimensional space. To this end, we develop a method, Human Mesh and Appearance Recovery (HMAR) which in addition to extracting the 3D geometry of the person as a SMPL mesh, also extracts appearance as a texture map on the triangles of the mesh. This serves as a 3D representation for appearance that is robust to viewpoint and pose changes. Given a video clip, we first detect bounding boxes corresponding to people, and for each one, we extract 3D appearance, pose, and location information using HMAR. These embedding vectors are then sent to a transformer, which performs spatio-temporal aggregation of the representations over the duration of the sequence. The similarity of the resulting representations is used to solve for associations that assigns each person to a tracklet. We evaluate our approach on the Posetrack, MuPoTs and AVA datasets. We find that 3D representations are more effective than 2D representations for tracking in these settings, and we obtain state-of-the-art performance. Code and results are available at: https://brjathu.github.io/T3DP.

In this work, we address the problem of multi-person 3D pose estimation from a single image. A typical regression approach in the top-down setting of this problem would first detect all humans and then reconstruct each one of them independently. However, this type of prediction suffers from incoherent results, e.g., interpenetration and inconsistent depth ordering between the people in the scene. Our goal is to train a single network that learns to avoid these problems and generate a coherent 3D reconstruction of all the humans in the scene. To this end, a key design choice is the incorporation of the SMPL parametric body model in our top-down framework, which enables the use of two novel losses. First, a distance field-based collision loss penalizes interpenetration among the reconstructed people. Second, a depth ordering-aware loss reasons about occlusions and promotes a depth ordering of people that leads to a rendering which is consistent with the annotated instance segmentation. This provides depth supervision signals to the network, even if the image has no explicit 3D annotations. The experiments show that our approach outperforms previous methods on standard 3D pose benchmarks, while our proposed losses enable more coherent reconstruction in natural images. The project website with videos, results, and code can be found at: https://jiangwenpl.github.io/multiperson.

This paper addresses the problem of 3D human pose and shape estimation from a single image. Previous approaches consider a parametric model of the human body, SMPL, and attempt to regress the model parameters that give rise to a mesh consistent with image evidence. This parameter regression has been a very challenging task, with model-based approaches underperforming compared to nonparametric solutions in terms of pose estimation. In our work, we propose to relax this heavy reliance on the model's parameter space. We still retain the topology of the SMPL template mesh, but instead of predicting model parameters, we directly regress the 3D location of the mesh vertices. This is a heavy task for a typical network, but our key insight is that the regression becomes significantly easier using a Graph-CNN. This architecture allows us to explicitly encode the template mesh structure within the network and leverage the spatial locality the mesh has to offer. Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location. Having recovered the complete 3D geometry of the mesh, if we still require a specific model parametrization, this can be reliably regressed from the vertices locations. We demonstrate the flexibility and the effectiveness of our proposed graph-based mesh regression by attaching different types of features on the mesh vertices. In all cases, we outperform the comparable baselines relying on model parameter regression, while we also achieve state-of-the-art results among model-based pose estimation approaches.

To facilitate the analysis of human actions, interactions and emotions, we compute a 3D model of human body pose, hand pose, and facial expression from a single monocular image. To achieve this, we use thousands of 3D scans to train a new, unified, 3D model of the human body, SMPL-X, that extends SMPL with fully articulated hands and an expressive face. Learning to regress the parameters of SMPL-X directly from images is challenging without paired images and 3D ground truth. Consequently, we follow the approach of SMPLify, which estimates 2D features and then optimizes model parameters to fit the features. We improve on SMPLify in several significant ways: (1) we detect 2D features corresponding to the face, hands, and feet and fit the full SMPL-X model to these; (2) we train a new neural network pose prior using a large MoCap dataset; (3) we define a new interpenetration penalty that is both fast and accurate; (4) we automatically detect gender and the appropriate body models (male, female, or neutral); (5) our PyTorch implementation achieves a speedup of more than 8x over Chumpy. We use the new method, SMPLify-X, to fit SMPL-X to both controlled images and images in the wild. We evaluate 3D accuracy on a new curated dataset comprising 100 images with pseudo ground-truth. This is a step towards automatic expressive human capture from monocular RGB data. The models, code, and data are available for research purposes at https://smpl-x.is.tue.mpg.de.

Model-based human pose estimation is currently approached through two different paradigms. Optimization-based methods fit a parametric body model to 2D observations in an iterative manner, leading to accurate image-model alignments, but are often slow and sensitive to the initialization. In contrast, regression-based methods, that use a deep network to directly estimate the model parameters from pixels, tend to provide reasonable, but not pixel accurate, results while requiring huge amounts of supervision. In this work, instead of investigating which approach is better, our key insight is that the two paradigms can form a strong collaboration. A reasonable, directly regressed estimate from the network can initialize the iterative optimization making the fitting faster and more accurate. Similarly, a pixel accurate fit from iterative optimization can act as strong supervision for the network. This is the core of our proposed approach SPIN (SMPL oPtimization IN the loop). The deep network initializes an iterative optimization routine that fits the body model to 2D joints within the training loop, and the fitted estimate is subsequently used to supervise the network. Our approach is self-improving by nature, since better network estimates can lead the optimization to better solutions, while more accurate optimization fits provide better supervision for the network. We demonstrate the effectiveness of our approach in different settings, where 3D ground truth is scarce, or not available, and we consistently outperform the state-of-the-art model-based pose estimation approaches by significant margins. The project website with videos, results, and code can be found at https://seas.upenn.edu/~nkolot/projects/spin.

This work addresses the problem of model-based human pose estimation. Recent approaches have made significant progress towards regressing the parameters of parametric human body models directly from images. Because of the absence of images with 3D shape ground truth, relevant approaches rely on 2D annotations or sophisticated architecture designs. In this work, we advocate that there are more cues we can leverage, which are available for free in natural images, i.e., without getting more annotations, or modifying the network architecture. We propose a natural form of supervision, that capitalizes on the appearance constancy of a person among different frames (or viewpoints). This seemingly insignificant and often overlooked cue goes a long way for model-based pose estimation. The parametric model we employ allows us to compute a texture map for each frame. Assuming that the texture of the person does not change dramatically between frames, we can apply a novel texture consistency loss, which enforces that each point in the texture map has the same texture value across all frames. Since the texture is transferred in this common texture map space, no camera motion computation is necessary, or even an assumption of smoothness among frames. This makes our proposed supervision applicable in a variety of settings, ranging from monocular video, to multi-view images. We benchmark our approach against strong baselines that require the same or even more annotations that we do and we consistently outperform them. Simultaneously, we achieve state-of-the-art results among model-based pose estimation approaches in different benchmarks. The project website with videos, results, and code can be found at https://seas.upenn.edu/~pavlakos/projects/texturepose.

Recovering 3D full-body human pose is a challenging problem with many applications. It has been successfully addressed by motion capture systems with body worn markers and multiple cameras. In this paper, we address the more challenging case of not only using a single camera but also not leveraging markers: going directly from 2D appearance to 3D geometry. Deep learning approaches have shown remarkable abilities to discriminatively learn 2D appearance features. The missing piece is how to integrate 2D, 3D, and temporal information to recover 3D geometry and account for the uncertainties arising from the discriminative model. We introduce a novel approach that treats 2D joint locations as latent variables whose uncertainty distributions are given by a deep fully convolutional neural network. The unknown 3D poses are modeled by a sparse representation and the 3D parameter estimates are realized via an Expectation-Maximization algorithm, where it is shown that the 2D joint location uncertainties can be conveniently marginalized out during inference. Extensive evaluation on benchmark datasets shows that the proposed approach achieves greater accuracy over state-of-the-art baselines. Notably, the proposed approach does not require synchronized 2D-3D data for training and is applicable to "in-the-wild" images, which is demonstrated with the MPII dataset.

Our ability to train end-to-end systems for 3D human pose estimation from single images is currently constrained by the limited availability of 3D annotations for natural images. Most datasets are captured using Motion Capture (MoCap) systems in a studio setting and it is difficult to reach the variability of 2D human pose datasets, like MPII or LSP. To alleviate the need for accurate 3D ground truth, we propose to use a weaker supervision signal provided by the ordinal depths of human joints. This information can be acquired by human annotators for a wide range of images and poses. We showcase the effectiveness and flexibility of training Convolutional Networks (ConvNets) with these ordinal relations in different settings, always achieving competitive performance with ConvNets trained with accurate 3D joint coordinates. Additionally, to demonstrate the potential of the approach, we augment the popular LSP and MPII datasets with ordinal depth annotations. This extension allows us to present quantitative and qualitative evaluation in non-studio conditions. Simultaneously, these ordinal annotations can be easily incorporated in the training procedure of typical ConvNets for 3D human pose. Through this inclusion we achieve new state-of-the-art performance for the relevant benchmarks and validate the effectiveness of ordinal depth supervision for 3D human pose.

This work addresses the problem of estimating the full body 3D human pose and shape from a single color image. This is a task where iterative optimization-based solutions have typically prevailed, while Convolutional Networks (ConvNets) have suffered because of the lack of training data and their low resolution 3D predictions. Our work aims to bridge this gap and proposes an efficient and effective direct prediction method based on ConvNets. Central part to our approach is the incorporation of a parametric statistical body shape model (SMPL) within our end-to-end framework. This allows us to get very detailed 3D mesh results, while requiring estimation only of a small number of parameters, making it friendly for direct network prediction. Interestingly, we demonstrate that these parameters can be predicted reliably only from 2D keypoints and masks. These are typical outputs of generic 2D human analysis ConvNets, allowing us to relax the massive requirement that images with 3D shape ground truth are available for training. Simultaneously, by maintaining differentiability, at training time we generate the 3D mesh from the estimated parameters and optimize explicitly for the surface using a 3D per-vertex loss. Finally, a differentiable renderer is employed to project the 3D mesh to the image, which enables further refinement of the network, by optimizing for the consistency of the projection with 2D annotations (i.e., 2D keypoints or masks). The proposed approach outperforms previous baselines on this task and offers an attractive solution for direct prediction of3D shape from a single color image.

Current motion capture (MoCap) systems generally require markers and multiple calibrated cameras, which can be used only in constrained environments. In this work we introduce a drone-based system for 3D human MoCap. The system only needs an autonomously flying drone with an on-board RGB camera and is usable in various indoor and outdoor environments. A reconstruction algorithm is developed to recover full-body motion from the video recorded by the drone. We argue that, besides the capability of tracking a moving subject, a flying drone also provides fast varying viewpoints, which is beneficial for motion reconstruction. We evaluate the accuracy of the proposed system using our new DroCap dataset and also demonstrate its applicability for MoCap in the wild using a consumer drone.

Recent advances with Convolutional Networks (ConvNets) have shifted the bottleneck for many computer vision tasks to annotated data collection. In this paper, we present a geometry-driven approach to automatically collect annotations for human pose prediction tasks. Starting from a generic ConvNet for 2D human pose, and assuming a multi-view setup, we describe an automatic way to collect accurate 3D human pose annotations. We capitalize on constraints offered by the 3D geometry of the camera setup and the 3D structure of the human body to probabilistically combine per view 2D ConvNet predictions into a globally optimal 3D pose. This 3D pose is used as the basis for harvesting annotations. The benefit of the annotations produced automatically with our approach is demonstrated in two challenging settings: (i) fine-tuning a generic ConvNet-based 2D pose predictor to capture the discriminative aspects of a subjects appearance (i.e.,personalization), and (ii) training a ConvNet from scratch for single view 3D human pose prediction without leveraging 3D pose groundtruth. The proposed multi-view pose estimator achieves state-of-the-art results on standard benchmarks, demonstrating the effectiveness of our method in exploiting the available multi-view information.

This paper addresses the challenge of 3D human pose estimation from a single color image. Despite the general success of the end-to-end learning paradigm, top performing approaches employ a two-step solution consisting of a Convolutional Network (ConvNet) for 2D joint localization and a subsequent optimization step to recover 3D pose. In this paper, we identify the representation of 3D pose as a critical issue with current ConvNet approaches and make two important contributions towards validating the value of end-to-end learning for this task. First, we propose a fine discretization of the 3D space around the subject and train a ConvNet to predict per voxel likelihoods for each joint. This creates a natural representation for 3D pose and greatly improves performance over the direct regression of joint coordinates. Second, to further improve upon initial estimates, we employ a coarse-to-fine prediction scheme. This step addresses the large dimensionality increase and enables iterative refinement and repeated processing of the image features. The proposed approach outperforms all state-of-the-art methods on standard benchmarks achieving a relative error reduction greater than 30% on average. Additionally, we investigate using our volumetric representation in a related architecture which is suboptimal compared to our end-to-end approach, but is of practical interest, since it enables training when no image with corresponding 3D groundtruth is available, and allows us to present compelling results for in-the-wild images.

This paper presents a novel approach to estimating the continuous six degree of freedom (6-DoF) pose (3D translation and rotation) of an object from a single RGB image. The approach combines semantic keypoints predicted by a convolutional network (convnet) with a deformable shape model. Unlike prior work, we are agnostic to whether the object is textured or textureless, as the convnet learns the optimal representation from the available training image data. Furthermore, the approach can be applied to instance- and class-based pose recovery. Empirically, we show that the proposed approach can accurately recover the 6-DoF object pose for both instance- and class-based scenarios with a cluttered background. For class-based object pose estimation, state-of-the-art accuracy is shown on the large-scale PASCAL3D+ dataset.

Axial symmetry is a common property of everyday objects. Bottles, cups, cans and bowls, all usually fall in that category and can be modeled by surfaces of revolution (SOR). In this paper, we address the problem of estimating the parameters of an SOR (axis and generatrix) from range data. Although SOR reconstruction from RGB images is well studied, previous works using depth measurements are limited. We propose a formulation similar to the 3D registration problem and our solution is based on an alternating procedure that recovers the complete surface geometry, i.e. The axis and the profile curve of the SOR. We evaluate our method both quantitatively and qualitatively using four different datasets that provide depth images from a large variety of axially symmetric objects.

We present a new framework for multimodal gesture recognition that is based on a two-pass fusion scheme. In this, we deal with a demanding Kinect-based multimodal dataset, which was introduced in a recent gesture recognition challenge. We employ multiple modalities, i.e., visual cues, such as colour and depth images, as well as audio, and we specifically extract feature descriptors of the hands' movement, handshape, and audio spectral properties. Based on these features, we statistically train separate unimodal gesture-word models, namely hidden Markov models, explicitly accounting for the dynamics of each modality. Multimodal recognition of unknown gesture sequences is achieved by combining these models in a late, two-pass fusion scheme that exploits a set of unimodally generated n-best recognition hypotheses. The proposed scheme achieves 88.2% gesture recognition accuracy in the Kinect-based multimodal dataset, outperforming all recently published approaches on the same challenging multimodal gesture recognition task.