Social EgoMesh Estimation

Accurately estimating the 3D pose of the camera wearer in egocentric video sequences is crucial to modeling human behavior in virtual and augmented reality applications. The task presents unique challenges due to the limited visibility of the user's body caused by the front-facing camera mounted on their head. Recent research has explored the utilization of the scene and ego-motion, but it has overlooked humans' interactive nature. We propose a novel framework for Social Egocentric Estimation of body MEshes (SEE-ME). Our approach is the first to estimate the wearer's mesh using only a latent probabilistic diffusion model, which we condition on the scene and, for the first time, on the social wearer-interactee interactions. Our in-depth study sheds light on when social interaction matters most for ego-mesh estimation; it quantifies the impact of interpersonal distance and gaze direction. Overall, SEE-ME surpasses the current best technique, reducing the pose estimation error (MPJPE) by 53%. The code is available at https://github.com/L-Scofano/SEEME.

CondiMen: Conditional Multi-Person Mesh Recovery

Multi-person human mesh recovery (HMR) consists in detecting all individuals in a given input image, and predicting the body shape, pose, and 3D location for each detected person. The dominant approaches to this task rely on neural networks trained to output a single prediction for each detected individual. In contrast, we propose CondiMen, a method that outputs a joint parametric distribution over likely poses, body shapes, intrinsics and distances to the camera, using a Bayesian network. This approach offers several advantages. First, a probability distribution can handle some inherent ambiguities of this task -- such as the uncertainty between a person's size and their distance to the camera, or simply the loss of information when projecting 3D data onto the 2D image plane. Second, the output distribution can be combined with additional information to produce better predictions, by using e.g. known camera or body shape parameters, or by exploiting multi-view observations. Third, one can efficiently extract the most likely predictions from the output distribution, making our proposed approach suitable for real-time applications. Empirically we find that our model i) achieves performance on par with or better than the state-of-the-art, ii) captures uncertainties and correlations inherent in pose estimation and iii) can exploit additional information at test time, such as multi-view consistency or body shape priors. CondiMen spices up the modeling of ambiguity, using just the right ingredients on hand.

HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features

Recent advancements in radiance field rendering show promising results in 3D scene representation, where Gaussian splatting-based techniques emerge as state-of-the-art due to their quality and efficiency. Gaussian splatting is widely used for various applications, including 3D human representation. However, previous 3D Gaussian splatting methods either use parametric body models as additional information or fail to provide any underlying structure, like human biomechanical features, which are essential for different applications. In this paper, we present a novel approach called HFGaussian that can estimate novel views and human features, such as the 3D skeleton, 3D key points, and dense pose, from sparse input images in real time at 25 FPS. The proposed method leverages generalizable Gaussian splatting technique to represent the human subject and its associated features, enabling efficient and generalizable reconstruction. By incorporating a pose regression network and the feature splatting technique with Gaussian splatting, HFGaussian demonstrates improved capabilities over existing 3D human methods, showcasing the potential of 3D human representations with integrated biomechanics. We thoroughly evaluate our HFGaussian method against the latest state-of-the-art techniques in human Gaussian splatting and pose estimation, demonstrating its real-time, state-of-the-art performance.

Leveraging Anthropometric Measurements to Improve Human Mesh Estimation and Ensure Consistent Body Shapes

The basic body shape of a person does not change within a single video. However, most SOTA human mesh estimation (HME) models output a slightly different body shape for each video frame, which results in inconsistent body shapes for the same person. In contrast, we leverage anthropometric measurements like tailors are already obtaining from humans for centuries. We create a model called A2B that converts such anthropometric measurements to body shape parameters of human mesh models. Moreover, we find that finetuned SOTA 3D human pose estimation (HPE) models outperform HME models regarding the precision of the estimated keypoints. We show that applying inverse kinematics (IK) to the results of such a 3D HPE model and combining the resulting body pose with the A2B body shape leads to superior and consistent human meshes for challenging datasets like ASPset or fit3D, where we can lower the MPJPE by over 30 mm compared to SOTA HME models. Further, replacing HME models estimates of the body shape parameters with A2B model results not only increases the performance of these HME models, but also leads to consistent body shapes.

Are Pose Estimators Ready for the Open World? STAGE: Synthetic Data Generation Toolkit for Auditing 3D Human Pose Estimators

The estimation of 3D human poses from images has progressed tremendously over the last few years as measured on standard benchmarks. However, performance in the open world remains underexplored, as current benchmarks cannot capture its full extent. Especially in safety-critical systems, it is crucial that 3D pose estimators are audited before deployment, and their sensitivity towards single factors or attributes occurring in the operational domain is thoroughly examined. Nevertheless, we currently lack a benchmark that would enable such fine-grained analysis. We thus present STAGE, a GenAI data toolkit for auditing 3D human pose estimators. We enable a text-to-image model to control the 3D human body pose in the generated image. This allows us to create customized annotated data covering a wide range of open-world attributes. We leverage STAGE and generate a series of benchmarks to audit the sensitivity of popular pose estimators towards attributes such as gender, ethnicity, age, clothing, location, and weather. Our results show that the presence of such naturally occurring attributes can cause severe degradation in the performance of pose estimators and leads us to question if they are ready for open-world deployment.

Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions

Understanding how humans interact with each other is key to building realistic multi-human virtual reality systems. This area remains relatively unexplored due to the lack of large-scale datasets. Recent datasets focusing on this issue mainly consist of activities captured entirely in controlled indoor environments with choreographed actions, significantly affecting their diversity. To address this, we introduce Harmony4D, a multi-view video dataset for human-human interaction featuring in-the-wild activities such as wrestling, dancing, MMA, and more. We use a flexible multi-view capture system to record these dynamic activities and provide annotations for human detection, tracking, 2D/3D pose estimation, and mesh recovery for closely interacting subjects. We propose a novel markerless algorithm to track 3D human poses in severe occlusion and close interaction to obtain our annotations with minimal manual intervention. Harmony4D consists of 1.66 million images and 3.32 million human instances from more than 20 synchronized cameras with 208 video sequences spanning diverse environments and 24 unique subjects. We rigorously evaluate existing state-of-the-art methods for mesh recovery and highlight their significant limitations in modeling close interaction scenarios. Additionally, we fine-tune a pre-trained HMR2.0 model on Harmony4D and demonstrate an improved performance of 54.8% PVE in scenes with severe occlusion and contact. Code and data are available at https://jyuntins.github.io/harmony4d/.

ActionPose: Pretraining 3D Human Pose Estimation with the Dark Knowledge of Action

2D-to-3D human pose lifting is an ill-posed problem due to depth ambiguity and occlusion. Existing methods relying on spatial and temporal consistency alone are insufficient to resolve these problems because they lack semantic information of the motions. To overcome this, we propose ActionPose, a framework that leverages action knowledge by aligning motion embeddings with text embeddings of fine-grained action labels. ActionPose operates in two stages: pretraining and fine-tuning. In the pretraining stage, the model learns to recognize actions and reconstruct 3D poses from masked and noisy 2D poses. During the fine-tuning stage, the model is further refined using real-world 3D human pose estimation datasets without action labels. Additionally, our framework incorporates masked body parts and masked time windows in motion modeling to mitigate the effects of ambiguous boundaries between actions in both temporal and spatial domains. Experiments demonstrate the effectiveness of ActionPose, achieving state-of-the-art performance in 3D pose estimation on public datasets, including Human3.6M and MPI-INF-3DHP. Specifically, ActionPose achieves an MPJPE of 36.7mm on Human3.6M with detected 2D poses as input and 15.5mm on MPI-INF-3DHP with ground-truth 2D poses as input.

Lost & Found: Updating Dynamic 3D Scene Graphs from Egocentric Observations

Recent approaches have successfully focused on the segmentation of static reconstructions, thereby equipping downstream applications with semantic 3D understanding. However, the world in which we live is dynamic, characterized by numerous interactions between the environment and humans or robotic agents. Static semantic maps are unable to capture this information, and the naive solution of rescanning the environment after every change is both costly and ineffective in tracking e.g. objects being stored away in drawers. With Lost & Found we present an approach that addresses this limitation. Based solely on egocentric recordings with corresponding hand position and camera pose estimates, we are able to track the 6DoF poses of the moving object within the detected interaction interval. These changes are applied online to a transformable scene graph that captures object-level relations. Compared to state-of-the-art object pose trackers, our approach is more reliable in handling the challenging egocentric viewpoint and the lack of depth information. It outperforms the second-best approach by 34% and 56% for translational and orientational error, respectively, and produces visibly smoother 6DoF object trajectories. In addition, we illustrate how the acquired interaction information in the dynamic scene graph can be employed in the context of robotic applications that would otherwise be unfeasible: We show how our method allows to command a mobile manipulator through teach & repeat, and how information about prior interaction allows a mobile manipulator to retrieve an object hidden in a drawer. Code, videos and corresponding data are accessible at https://behretj.github.io/LostAndFound.

Towards Multi-Modal Animal Pose Estimation: An In-Depth Analysis

Animal pose estimation (APE) aims to locate the animal body parts using a diverse array of sensor and modality inputs, which is crucial for research across neuroscience, biomechanics, and veterinary medicine. By evaluating 178 papers since 2013, APE methods are categorised by sensor and modality types, learning paradigms, experimental setup, and application domains, presenting detailed analyses of current trends, challenges, and future directions in single- and multi-modality APE systems. The analysis also highlights the transition between human and animal pose estimation. Additionally, 2D and 3D APE datasets and evaluation metrics based on different sensors and modalities are provided. A regularly updated project page is provided here: https://github.com/ChennyDeng/MM-APE.

Self Supervised Networks for Learning Latent Space Representations of Human Body Scans and Motions

This paper introduces self-supervised neural network models to tackle several fundamental problems in the field of 3D human body analysis and processing. First, we propose VariShaPE (Varifold Shape Parameter Estimator), a novel architecture for the retrieval of latent space representations of body shapes and poses. This network offers a fast and robust method to estimate the embedding of arbitrary unregistered meshes into the latent space. Second, we complement the estimation of latent codes with MoGeN (Motion Geometry Network) a framework that learns the geometry on the latent space itself. This is achieved by lifting the body pose parameter space into a higher dimensional Euclidean space in which body motion mini-sequences from a training set of 4D data can be approximated by simple linear interpolation. Using the SMPL latent space representation we illustrate how the combination of these network models, once trained, can be used to perform a variety of tasks with very limited computational cost. This includes operations such as motion interpolation, extrapolation and transfer as well as random shape and pose generation.