We propose a novel diffusion-based framework for reconstructing 3D geometry of hand-held objects from monocular RGB images by leveraging hand-object interaction as geometric guidance. Our method conditions a latent diffusion model on an inpainted object appearance and uses inference-time guidance to optimize the object reconstruction, while simultaneously ensuring plausible hand-object interactions. Unlike prior methods that rely on extensive post-processing or produce low-quality reconstructions, our approach directly generates high-quality object geometry during the diffusion process by introducing guidance with an optimization-in-the-loop design. Specifically, we guide the diffusion model by applying supervision to the velocity field while simultaneously optimizing the transformations of both the hand and the object being reconstructed. This optimization is driven by multi-modal geometric cues, including normal and depth alignment, silhouette consistency, and 2D keypoint reprojection. We further incorporate signed distance field supervision and enforce contact and non-intersection constraints to ensure physical plausibility of hand-object interaction. Our method yields accurate, robust and coherent reconstructions under occlusion while generalizing well to in-the-wild scenarios. The project page is at https://aidilayce.github.io/FollowMyHold-page/.

We present locality-sensitive avatar, a neural radiance field (NeRF) based network to learn human motions from monocular videos. To this end, we estimate a canonical representation between different frames of a video with a non-linear mapping from observation to canonical space, which we decompose into a skeletal rigid motion and a non-rigid counterpart. Our key contribution is to retain fine-grained details by modeling the non-rigid part with a graph neural network (GNN) that keeps the pose information local to neighboring body parts. Compared to former canonical representation based methods which solely operate on the coordinate space of a whole shape, our locality-sensitive motion modeling can reproduce both realistic shape contours and vivid fine-grained details. We evaluate on ZJU-MoCap, SynWild, ActorsHQ, MVHumanNet and various outdoor videos. The experiments reveal that with the locality sensitive deformation to canonical feature space, we are the first to achieve state-of-the-art results across novel view synthesis, novel pose animation and 3D shape reconstruction simultaneously. Our code is available at https://github.com/ChunjinSong/lsavatar.

We introduce the first method for audio-driven universal photorealistic avatar synthesis, combining a person-agnostic speech model with our novel Universal Head Avatar Prior (UHAP). UHAP is trained on cross-identity multi-view videos. In particular, our UHAP is supervised with neutral scan data, enabling it to capture the identity-specific details at high fidelity. In contrast to previous approaches, which predominantly map audio features to geometric deformations only while ignoring audio-dependent appearance variations, our universal speech model directly maps raw audio inputs into the UHAP latent expression space. This expression space inherently encodes, both, geometric and appearance variations. For efficient personalization to new subjects, we employ a monocular encoder, which enables lightweight regression of dynamic expression variations across video frames. By accounting for these expression-dependent changes, it enables the subsequent model fine-tuning stage to focus exclusively on capturing the subject’s global appearance and geometry. Decoding these audio-driven expression codes via UHAP generates highly realistic avatars with precise lip synchronization and nuanced expressive details, such as eyebrow movement, gaze shifts, and realistic mouth interior appearance as well as motion. Extensive evaluations demonstrate that our method is not only the first generalizable audio-driven avatar model that can account for detailed appearance modeling and rendering, but it also outperforms competing (geometry-only) methods across metrics measuring lip-sync accuracy, quantitative image quality, and perceptual realism.

Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and furniture, will not be captured by the original model. This has led to interest in how to personalize a text-to-image model. Despite significant progress, this task remains a formidable challenge, particularly in preserving the subject's identity. Most researchers attempt to address this issue by modifying model architectures. These methods are capable of keeping the subject structure and color but fail to preserve identity details. Towards this issue, our approach takes a data-centric perspective. We introduce a novel regularization dataset generation strategy on both the text and image level. This strategy enables the model to preserve fine details of the desired subjects, such as text and logos. Our method is architecture-agnostic and can be flexibly applied on various text-to-image models. We show on established benchmarks that our data-centric approach forms the new state of the art in terms of identity preservation and text alignment.

Abstract For reconstructing high‐fidelity human 3D models from monocular videos, it is crucial to maintain consistent large‐scale body shapes along with finely matched subtle wrinkles. This paper explores how per‐frame rendering results can be factorized into a pose‐independent component and a corresponding pose‐dependent counterpart to facilitate frame consistency at multiple scales. Pose adaptive texture features are further improved by restricting the frequency bands of these two components. Pose‐independent outputs are expected to be low‐frequency, while high‐frequency information is linked to pose‐dependent factors. We implement this with a dual‐branch network. The first branch takes coordinates in the canonical space as input, while the second one additionally considers features outputted by the first branch and pose information of each frame. A final network integrates the information predicted by both branches and utilizes volume rendering to generate photo‐realistic 3D human images. Through experiments, we demonstrate that our method consistently surpasses all state‐of‐the‐art methods in preserving high‐frequency details and ensuring consistent body contours. Our code is accessible at https://github.com/ChunjinSong/facavatar .

Human motion capture either requires multi-camera systems or is unreliable when using single-view input due to depth ambiguities. Meanwhile, mirrors are readily available in urban environments and form an affordable alternative by recording two views with only a single camera. However, the mirror setting poses the additional challenge of handling occlusions of real and mirror image. Going beyond existing mirror approaches for 3D human pose estimation, we utilize mirrors for learning a complete body model, including shape and dense appearance. Our main contributions are extending articulated neural radiance fields to include a notion of a mirror, making it sample-efficient over potential occlusion regions. Together, our contributions realize a consumer-level 3D motion capture system that starts from off-the-shelf 2D poses by automatically calibrating the camera, estimating mirror orientation, and subsequently lifting 2D keypoint detections to 3D skeleton pose that is used to condition the mirror-aware NeRF. We empirically demonstrate the benefit of learning a body model and accounting for occlusion in challenging mirror scenes. The project is available at: https://danielajisafe.github.io/mirror-aware-neural-humans/.

Neural character models can now reconstruct detailed geometry and texture from video, but they lack explicit shadows and shading, leading to artifacts when generating novel views and poses or during relighting. It is particularly difficult to include shadows as they are a global effect and the required casting of secondary rays is costly. We propose a new shadow model using a Gaussian density proxy that replaces sampling with a simple analytic formula. It supports dynamic motion and is tailored for shadow computation, thereby avoiding the affine projection approximation and sorting required by the closely related Gaussian splatting. Combined with a deferred neural rendering model, our Gaussian shadows enable Lambertian shading and shadow casting with minimal overhead. We demonstrate improved reconstructions, with better separation of albedo, shading, and shadows in challenging outdoor scenes with direct sun light and hard shadows. Our method is able to optimize the light direction without any input from the user. As a result, novel poses have fewer shadow artifacts, and relighting in novel scenes is more realistic compared to the state-of-the-art methods, providing new ways to pose neural characters in novel environments, increasing their applicability. Code available at: https://github.com/LuisBolanos17/GaussianShadowCasting

Unsupervised learning of keypoints and landmarks has seen significant progress with the help of modern neural network architectures, but performance is yet to match the supervised counterpart, making their practicability questionable. We leverage the emergent knowledge within text-to-image diffusion models, towards more robust unsupervised keypoints. Our core idea is to find text embeddings that would cause the generative model to consistently attend to compact regions in images (i.e. keypoints). To do so, we simply optimize the text embedding such that the cross-attention maps within the denoising network are localized as Gaussians with small standard deviations. We validate our performance on multiple datasets: the CelebA, CUB-200-2011, Tai-Chi-HD, DeepFashion, and Human3.6m datasets. We achieve significantly improved accuracy, sometimes even outperforming supervised ones, particularly for data that is non-aligned and less curated. Our code is publicly available at the project page.

It is now possible to estimate 3D human pose from monocular images with off-the-shelf 3D pose estimators. However, many practical applications require fine-grained absolute pose information for which multi-view cues and camera calibration are necessary. Such multi-view recordings are laborious because they require manual calibration, and are expensive when using dedicated hardware. Our goal is full automation, which includes temporal synchronization, as well as intrinsic and extrinsic camera calibration. This is done by using persons in the scene as the calibration objects. Existing methods either address only synchronization or calibration, assume one of the former as input, or have significant limitations. A common limitation is that they only consider single persons, which eases correspondence finding. We attain this generality by partitioning the high-dimensional time and calibration space into a cascade of subspaces and introduce tailored algorithms to optimize each efficiently and robustly. The outcome is an easy-to-use, flexible, and robust motion capture toolbox that we release to enable scientific applications, which we demonstrate on diverse multi-view benchmarks. Project website: https://github.com/tangytoby/CasCalib.

It is now possible to reconstruct dynamic human motion and shape from a sparse set of cameras using Neural Radiance Fields (NeRF) driven by an underlying skeleton. However, a challenge remains to model the deformation of cloth and skin in relation to skeleton pose. Unlike existing avatar models that are learned implicitly or rely on a proxy surface, our approach is motivated by the observation that different poses necessitate unique frequency assignments. Neglecting this distinction yields noisy artifacts in smooth areas or blurs fine-grained texture and shape details in sharp regions. We develop a two-branch neural network that is adaptive and explicit in the frequency domain. The first branch is a graph neural network that models correlations among body parts locally, taking skeleton pose as input. The second branch combines these correlation features to a set of global frequencies and then modulates the feature encoding. Our experiments demonstrate that our network outperforms state-of-the-art methods in terms of preserving details and generalization capabilities. Our code is available at https://github.com/ChunjinSong/PM-Avatars.

Supervised keypoint localization methods rely on large manually labeled image datasets, where objects can deform, articulate, or occlude. However, creating such large keypoint labels is time-consuming and costly, and is often error-prone due to inconsistent labeling. Thus, we desire an approach that can learn keypoint localization with fewer yet consistently annotated images. To this end, we present a novel formulation that learns to localize semantically consistent keypoint definitions, even for occluded regions, for varying object categories. We use a few user-labeled 2D images as input examples, which are extended via self-supervision using a larger unlabeled dataset. Unlike unsupervised methods, the few-shot images act as semantic shape constraints for object localization. Furthermore, we introduce 3D geometry-aware constraints to uplift keypoints, achieving more accurate 2D localization. Our general-purpose formulation paves the way for semantically conditioned generative modeling and attains competitive or state-of-the-art accuracy on several datasets, including human faces, eyes, animals, cars, and never-before-seen mouth interior (teeth) localization tasks, not attempted by the previous few-shot methods. Project page: https://xingzhehe.github.io/FewShot3DKP/

High-fidelity human 3D models can now be learned directly from videos, typically by combining a template-based surface model with neural representations. However, obtaining a template surface requires expensive multi-view capture systems, laser scans, or strictly controlled conditions. Previous methods avoid using a template but rely on a costly or ill-posed mapping from observation to canonical space. We propose a hybrid point-based representation for reconstructing animatable characters that does not require an explicit surface model, while being generalizable to novel poses. For a given video, our method automatically produces an explicit set of 3D points representing approximate canonical geometry, and learns an articulated deformation model that produces pose-dependent point transformations. The points serve both as a scaffold for high-frequency neural features and an anchor for efficiently mapping between observation and canonical space. We demonstrate on established benchmarks that our representation overcomes limitations of prior work operating in either canonical or in observation space. Moreover, our automatic point extraction approach enables learning models of human and animal characters alike, matching the performance of the methods using rigged surface templates despite being more general. Project website: https://lemonatsu.github.io/npc/.

A long-standing goal in the field of sensory substitution is enabling sound perception for deaf and hard of hearing (DHH) people by visualizing audio content. Different from existing models that translate to hand sign language, between speech and text, or text and images, we target immediate and low-level audio to video translation that applies to generic environment sounds as well as human speech. Since such a substitution is artificial, with-out labels for supervised learning, our core contribution is to build a mapping from audio to video that learns from unpaired examples via high-level constraints. For speech, we additionally disentangle content from style, such as gender and dialect. Qualitative and quantitative results, including a human study, demonstrate that our unpaired translation approach maintains important audio features in the generated video and that videos of faces and numbers are well suited for visualizing high-dimensional audio features that can be parsed by humans to match and distinguish between sounds and words. Project website: https://chunjinsong.github.io/audioviewer

Recent neural rendering approaches greatly improve image quality, reaching near photorealism. However, the underlying neural networks have high runtime, precluding telepresence and virtual reality applications that require high resolution at low latency. The sequential dependency of layers in deep networks makes their optimization difficult. We break this dependency by caching information from the previous frame to speed up the processing of the current one with an implicit warp. The warping with a shallow network reduces latency and the caching operations can further be parallelized to improve the frame rate. In contrast to existing temporal neural networks, ours is tailored for the task of rendering novel views of faces by conditioning on the change of the underlying surface mesh. We test the approach on view-dependent rendering of 3D portrait avatars, as needed for telepresence, on established benchmark sequences. Warping reduces latency by 70% (from 49.4ms to 14.9ms on commodity GPUs) and scales frame rates accordingly over multiple GPUs while reducing image quality by only 1%, making it suitable as part of end-to-end view-dependent 3D teleconferencing applications.

In this article we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich latent vectors. Instead of simply treating the latent features of nearby frames as positive pairs and those of temporally-distant ones as negative pairs as in other CSS approaches, we explicitly disentangle each latent vector into a time-variant component and a time-invariant one. We then show that applying contrastive loss only to the time-variant features and encouraging a gradual transition on them between nearby and away frames while also reconstructing the input, extract rich temporal features, well-suited for human pose estimation. Our approach reduces error by about 50% compared to the standard CSS strategies, outperforms other unsupervised single-view methods and matches the performance of multi-view techniques. When 2D pose is available, our approach can extract even richer latent features and improve the 3D pose estimation accuracy, outperforming other state-of-the-art weakly supervised methods.

This paper addresses the problem of cross-dataset generalization of 3D human pose estimation models. Testing a pre-trained 3D pose estimator on a new dataset results in a major performance drop. Previous methods have mainly addressed this problem by improving the diversity of the training data. We argue that diversity alone is not sufficient and that the characteristics of the training data need to be adapted to those of the new dataset such as camera view-point, position, human actions, and body size. To this end, we propose AdaptPose, an end-to-end framework that generates synthetic 3D human motions from a source dataset and uses them to fine-tune a 3D pose estimator. AdaptPose follows an adversarial training scheme. From a source 3D pose the generator generates a sequence of 3D poses and a camera orientation that is used to project the generated poses to a novel view. Without any 3D labels or camera information AdaptPose successfully learns to create synthetic 3D poses from the target dataset while only being trained on 2D poses. In experiments on the Human3.6M, MPI-INF-3DHp, 3DPW, and Ski-Pose datasets our method outperforms previous work in cross-dataset evaluations by 14% and previous semi-supervised learning methods that use partial 3D annotations by 16%.

Segmenting an image into its parts is a common pre-process for high-level vision tasks such as image editing. However, annotating masks for supervised training is expensive. Weakly-supervised and unsupervised methods exist, but they depend on the comparison of pairs of images, such as from multi-views, frames of videos, and image augmentation, which limit their applicability. To address this, we propose a GAN-based approach that generates images conditioned on latent masks, thereby alleviating full or weak annotations required by previous approaches. We show that such mask-conditioned image generation can be learned faithfully when conditioning the masks in a hierarchical manner on 2D latent points that define the position of parts explicitly. Without requiring supervision of masks or points, this strategy increases robustness of mask to viewpoint and object position changes. It also lets us generate image-mask pairs for training a segmentation network, which outperforms state-of-the-art unsupervised segmentation methods on established benchmarks. Code can be found at https://github.com/xingzhehe/GANSeg.

Human pose estimation from single images is a challenging problem that is typically solved by supervised learning. Unfortunately, labeled training data does not yet exist for many human activities since 3D annotation requires dedicated motion capture systems. Therefore, we propose an unsupervised approach that learns to predict a 3D human pose from a single image while only being trained with 2D pose data, which can be crowd-sourced and is already widely available. To this end, we estimate the 3D pose that is most likely over random projections, with the likelihood estimated using normalizing flows on 2D poses. While previous work requires strong priors on camera rotations in the training data set, we learn the distribution of camera angles which significantly improves the performance. Another part of our contribution is to stabilize training with normalizing flows on high-dimensional 3D pose data by first projecting the 2D poses to a linear subspace. We outperform the state-of-the-art unsupervised human pose estimation methods on the benchmark datasets Human3.6M and MPI-INF-3DHP in many metrics.

Many algorithmic approaches to 3D acoustic imaging have been devised which rely on a large abundance of receiving elements to produce images with delay-and-sum techniques, but these have found little use in air due to hardware complexity and low accuracy. Recent learning-based approaches to one-shot in-air acoustic reconstruction attempt to overcome these limitations using simple hardware and large datasets of geometry and echo pairs to train neural networks. How-ever, existing learned models use spatially-dense representations and attempt to predict entire scenes at once, requiring an abundance of data to truly generalize.We train an implicit neural network with no spatial awareness to predict the distance to the nearest obstacle at a single location from only time-delayed echoes. Using acoustic wave simulation, we show that our method yields better generalization and behaves more intuitively than competing methods while requiring only a fraction of the training data. Our code and data is available at https://timstr.github.io/learned-acoustic-reconstruction/.

Structured representations such as keypoints are widely used in pose transfer, conditional image generation, animation, and 3D reconstruction. However, their supervised learning requires expensive annotation for each target domain. We propose a self-supervised method that learns to disentangle object structure from the appearance with a graph of 2D keypoints linked by straight edges. Both the keypoint location and their pairwise edge weights are learned, given only a collection of images depicting the same object class. The resulting graph is interpretable, for example, AutoLink recovers the human skeleton topology when applied to images showing people. Our key ingredients are i) an encoder that predicts keypoint locations in an input image, ii) a shared graph as a latent variable that links the same pairs of keypoints in every image, iii) an intermediate edge map that combines the latent graph edge weights and keypoint locations in a soft, differentiable manner, and iv) an inpainting objective on randomly masked images. Although simpler, AutoLink outperforms existing self-supervised methods on the established keypoint and pose estimation benchmarks and paves the way for structure-conditioned generative models on more diverse datasets. Project website: https://xingzhehe.github.io/autolink/.

While supervised object detection and segmentation methods achieve impressive accuracy, they generalize poorly to images whose appearance significantly differs from the data they have been trained on. To address this when annotating data is prohibitively expensive, we introduce a self-supervised detection and segmentation approach that can work with single images captured by a potentially moving camera. At the heart of our approach lies the observation that object segmentation and background reconstruction are linked tasks, and that, for structured scenes, background regions can be re-synthesized from their surroundings, whereas regions depicting the moving object cannot. We encode this intuition into a self-supervised loss function that we exploit to train a proposal-based segmentation network. To account for the discrete nature of the proposals, we develop a Monte Carlo-based training strategy that allows the algorithm to explore the large space of object proposals. We apply our method to human detection and segmentation in images that visually depart from those of standard benchmarks and outperform existing self-supervised methods.

Many sketch processing applications target precise vector drawings with accurately specified stroke intersections, yet free-form artist drawn sketches are typically inexact: strokes that are intended to intersect often stop short of doing so. While human observers easily perceive the artist intended stroke connectivity, manually, or even semi-manually, correcting drawings to generate correctly connected outputs is tedious and highly time consuming. We propose a novel, robust algorithm that extracts viewer-perceived stroke connectivity from inexact free-form vector drawings by leveraging observations about local and global factors that impact human perception of inter-stroke connectivity. We employ the identified local cues to train classifiers that assess the likelihood that pairs of strokes are perceived as forming end-to-end or T- junctions based on local context. We then use these classifiers within an incremental framework that combines classifier provided likelihoods with a more global, contextual and closure-based, analysis. We demonstrate our method on over 95 diversely sourced inputs, and validate it via a series of perceptual studies; participants prefer our outputs over the closest alternative by a factor of 9 to 1.

Human pose estimation from single images is a challenging problem in computer vision that requires large amounts of labeled training data to be solved accurately. Unfortunately, for many human activities (e.g. outdoor sports) such training data does not exist and is hard or even impossible to acquire with traditional motion capture systems. We propose a self-supervised approach that learns a single image 3D pose estimator from unlabeled multi-view data. To this end, we exploit multi-view consistency constraints to disentangle the observed 2D pose into the underlying 3D pose and camera rotation. In contrast to most existing methods, we do not require calibrated cameras and can therefore learn from moving cameras. Nevertheless, in the case of a static camera setup, we present an optional extension to include constant relative camera rotations over multiple views into our framework. Key to the success are new, unbiased reconstruction objectives that mix information across views and training samples. The proposed approach is evaluated on two benchmark datasets (Human3.6M and MPII-INF-3DHP) and on the in-the-wild SkiPose dataset.

Local processing is an essential feature of CNNs and other neural network architectures—it is one of the reasons why they work so well on images where relevant information is, to a large extent, local. However, perspective effects stemming from the projection in a conventional camera vary for different global positions in the image. We introduce Perspective Crop Layers (PCLs)—a form of perspective crop of the region of interest based on the camera geometry— and show that accounting for the perspective consistently improves the accuracy of state-of-the-art 3D pose reconstruction methods. PCLs are modular neural network layers, which, when inserted into existing CNN and MLP architectures, deterministically remove the location-dependent perspective effects while leaving end-to-end training and the number of parameters of the underlying neural network unchanged. We demonstrate that PCL leads to improved 3D human pose reconstruction accuracy for CNN architectures that use cropping operations, such as spatial transformer networks (STN), and, somewhat surprisingly, MLPs used for 2D-to-3D key-point lifting. Our conclusion is that it is important to utilize camera calibration information when available, for classical and deep-learning-based computer vision alike. PCL offers an easy way to improve the accuracy of existing 3D reconstruction networks by making them geometry-aware. Our code is publicly available at github.com/yu-frank/PerspectiveCropLayers.

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion.For scenes with dynamic activities and camera motion, we propose a multi-camera framework in which geometric constraints are embedded in the form of multi-view consistency during training via coarse 3D localization in a voxel grid and fine-grained offset regression. In this manner, we learn a joint distribution of proposals over multiple views. At inference time, our method operates on single RGB images. We outperform state-of-the-art techniques both on images that visually depart from those of standard benchmarks and on those of the classical Human3.6M dataset.

While deep learning reshaped the classical motion capture pipeline with feed-forward networks, generative models are required to recover fine alignment via iterative refinement. Unfortunately, the existing models are usually hand-crafted or learned in controlled conditions, only applicable to limited domains. We propose a method to learn a generative neural body model from unlabelled monocular videos by extending Neural Radiance Fields (NeRFs). We equip them with a skeleton to apply to time-varying and articulated motion. A key insight is that implicit models require the inverse of the forward kinematics used in explicit surface models. Our reparameterization defines spatial latent variables relative to the pose of body parts and thereby overcomes ill-posed inverse operations with an overparameterization. This enables learning volumetric body shape and appearance from scratch while jointly refining the articulated pose; all without ground truth labels for appearance, pose, or 3D shape on the input videos. When used for novel-view-synthesis and motion capture, our neural model improves accuracy on diverse datasets.

While general object detection has seen tremendous progress, localization of elliptical objects has received little attention in the literature. Our motivating application is the detection of knots in sawn lumber images, which is an important problem since the number and types of knots are visual characteristics that adversely affect the quality of sawn lumber. We demonstrate how models can be tailored to the elliptical shape and thereby improve on general purpose detectors; more generally, elliptical defects are common in industrial production, such as enclosed air bubbles when casting glass or plastic. In this paper, we adapt the Faster R-CNN with its Region Proposal Network (RPN) to model elliptical objects with a Gaussian function, and extend the existing Gaussian Proposal Network (GPN) architecture by adding the region-of-interest pooling and regression branches, as well as using the Wasserstein distance as the loss function to predict the precise locations of elliptical objects. Our proposed method has promising results on the lumber knot dataset: knots are detected with an average intersection over union of 73.05%, compared to 63.63% for general purpose detectors. Specific to the lumber application, we also propose an algorithm to correct any misalignment in the raw lumber images during scanning, and contribute the first open-source lumber knot dataset by labeling the elliptical knots in the preprocessed images.

The accuracy of monocular 3D human pose estimation depends on the viewpoint from which the image is captured. While freely moving cameras, such as on drones, provide control over this viewpoint, automatically positioning them at the location which will yield the highest accuracy remains an open problem. This is the problem that we address in this paper. Specifically, given a short video sequence, we introduce an algorithm that predicts which viewpoints should be chosen to capture future frames so as to maximize 3D human pose estimation accuracy. The key idea underlying our approach is a method to estimate the uncertainty of the 3D body pose estimates. We integrate several sources of uncertainty, originating from deep learning based regressors and temporal smoothness. Our motion planner yields improved 3D body pose estimates and outperforms or matches existing ones that are based on person following and orbiting.

Our goal is to capture the pose of real animals using synthetic training examples, without using any manual supervision. Our focus is on neuroscience model organisms, to be able to study how neural circuits orchestrate behaviour. Human pose estimation attains remarkable accuracy when trained on real or simulated datasets consisting of millions of frames. However, for many applications simulated models are unrealistic and real training datasets with comprehensive annotations do not exist. We address this problem with a new sim2real domain transfer method. Our key contribution is the explicit and independent modeling of appearance, shape and pose in an unpaired image translation framework. Our model lets us train a pose estimator on the target domain by transferring readily available body keypoint locations from the source domain to generated target images. We compare our approach with existing domain transfer methods and demonstrate improved pose estimation accuracy on Drosophila melanogaster (fruit fly), Caenorhabditis elegans (worm) and Danio rerio (zebrafish), without requiring any manual annotation on the target domain and despite using simplistic off-the-shelf animal characters for simulation, or simple geometric shapes as models. Our new datasets, code and trained models will be published to support future computer vision and neuroscientific studies.

Reconstruction of a 3D shape from a single 2D image is a classical computer vision problem, whose difficulty stems from the inherent ambiguity of recovering occluded or only partially observed surfaces. Recent methods address this challenge through the use of largely unstructured neural networks that effectively distill conditional mapping and priors over 3D shape. In this work, we induce structure and geometric constraints by leveraging three core observations: (1) the surface of most everyday objects is often almost entirely exposed from pairs of typical opposite views; (2) everyday objects often exhibit global reflective symmetries which can be accurately predicted from single views; (3) opposite orthographic views of a 3D shape share consistent silhouettes. Following these observations, we first predict orthographic 2.5D visible surface maps (depth, normal and silhouette) from perspective 2D images, and detect global reflective symmetries in this data; second, we predict the back facing depth and normal maps using as input the front maps and, when available, the symmetric reflections of these maps; and finally, we reconstruct a 3D mesh from the union of these maps using a surface reconstruction method best suited for this data. Our experiments demonstrate that our framework outperforms state-of-the art approaches for 3D shape reconstructions from 2D and 2.5D data in terms of input fidelity and details preservation. Specifically, we achieve 12% better performance on average in ShapeNet benchmark dataset, and up to 19% for certain classes of objects (e.g., chairs and vessels).

We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions by objects and by other people. Our method operates in subsequent stages. The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net , that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy. In the second stage, a fullyconnected neural network turns the possibly partial (on account of occlusion) 2D pose and 3D pose features for each subject into a complete 3D pose estimate per individual. The third stage applies space-time skeletal model fitting to the predicted 2D and 3D pose per subject to further reconcile the 2D and 3D pose, and enforce temporal coherence. Our method returns the full skeletal pose in joint angles for each subject. This is a further key distinction from previous work that do not produce joint angle results of a coherent skeleton in real time for multi-person scenes. The proposed system runs on consumer hardware at a previously unseen speed of more than 30 fps given 512x320 images as input while achieving state-of-the-art accuracy, which we will demonstrate on a range of challenging real-world scenes.

In sports, such as alpine skiing, coaches would like to know the speed and various biomechanical variables of their athletes and competitors. Existing methods use either body-worn sensors, which are cumbersome to setup, or manual image annotation, which is time consuming. We propose a method for estimating an athlete's global 3D position and articulated pose using multiple cameras. By contrast to classical markerless motion capture solutions, we allow cameras to rotate freely so that large capture volumes can be covered. In a first step, tight crops around the skier are predicted and fed to a 2D pose estimator network. The 3D pose is then reconstructed using a bundle adjustment method. Key to our solution is the rotation estimation of Pan-Tilt cameras in a joint optimization with the athlete pose and conditioning on relative background motion computed with feature tracking. Furthermore, we created a new alpine skiing dataset and annotated it with 2D pose labels, to overcome shortcomings of existing ones. Our method estimates accurate global 3D poses from images only and provides coaches with an automatic and fast tool for measuring and improving an athlete's performance.

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because the learned features are a valuable starting point to learn from limited labeled data. However, when it comes to 3D motion capture of multiple people, these features are only of limited use. In this paper, we therefore propose an approach to learning features that are useful for this purpose. To this end, we introduce a self-supervised approach to learning what we call a neural scene decomposition (NSD) that can be exploited for 3D pose estimation. NSD comprises three layers of abstraction to represent human subjects: spatial layout in terms of bounding-boxes and relative depth; a 2D shape representation in terms of an instance segmentation mask; and subject-specific appearance and 3D pose information. By exploiting self-supervision coming from multiview data, our NSD model can be trained end-to-end without any 2D or 3D supervision. In contrast to previous approaches, it works for multiple persons and full-frame images. Because it encodes 3D geometry, NSD can then be effectively leveraged to train a 3D pose estimation network from small amounts of annotated data.

Estimating the metric height of a person from monocular imagery without additional assumptions is ill-posed. Existing solutions either require manual calibration of ground plane and camera geometry, special cameras, or reference objects of known size. We focus on motion cues and exploit gravity on earth as an omnipresent reference 'object' to translate acceleration, and subsequently height, measured in image-pixels to values in meters. We require videos of motion as input, where gravity is the only external force. This limitation is different to those of existing solutions that recover a person's height and, therefore, our method opens up new application fields. We show theoretically and empirically that a simple motion trajectory analysis suffices to translate from pixel measurements to the person's metric height, reaching a MAE of up to 3.9 cm on jumping motions, and that this works without camera and ground plane calibration.

We propose the first real-time system for the egocentric estimation of 3D human body pose in a wide range of unconstrained everyday activities. This setting has a unique set of challenges, such as mobility of the hardware setup, and robustness to long capture sessions with fast recovery from tracking failures. We tackle these challenges based on a novel lightweight setup that converts a standard baseball cap to a device for high-quality pose estimation based on a single cap-mounted fisheye camera. From the captured egocentric live stream, our CNN based 3D pose estimation approach runs at 60 Hz on a consumer-level GPU. In addition to the lightweight hardware setup, our other main contributions are: 1) a large ground truth training corpus of top-down fisheye images and 2) a disentangled 3D pose estimation approach that takes the unique properties of the egocentric viewpoint into account. As shown by our evaluation, we achieve lower 3D joint error as well as better 2D overlay than the existing baselines.

Accurate 3D human pose estimation from single images is possible with sophisticated deep-net architectures that have been trained on very large datasets. However, this still leaves open the problem of capturing motions for which no such database exists. Manual annotation is tedious, slow, and error-prone. In this paper, we propose to replace most of the annotations by the use of multiple views, at training time only. Specifically, we train the system to predict the same pose in all views. Such a consistency constraint is necessary but not sufficient to predict accurate poses. We therefore complement it with a supervised loss aiming to predict the correct pose in a small set of labeled images, and with a regularization term that penalizes drift from initial predictions. Furthermore, we propose a method to estimate camera pose jointly with human pose, which lets us utilize multiview footage where calibration is difficult, e.g., for pan-tilt or moving handheld cameras. We demonstrate the effectiveness of our approach on established benchmarks, as well as on a new Ski dataset with rotating cameras and expert ski motion, for which annotations are truly hard to obtain.

Modern 3D human pose estimation techniques rely on deep networks, which require large amounts of training data. While weakly-supervised methods require less supervision, by utilizing 2D poses or multi-view imagery without annotations, they still need a sufficiently large set of samples with 3D annotations for learning to succeed. In this paper, we propose to overcome this problem by learning a geometry-aware body representation from multi-view images without annotations. To this end, we use an encoder-decoder that predicts an image from one viewpoint given an image from another viewpoint. Because this representation encodes 3D geometry, using it in a semi-supervised setting makes it easier to learn a mapping from it to 3D human pose. As evidenced by our experiments, our approach significantly outperforms fully-supervised methods given the same amount of labeled data, and improves over other semi-supervised methods while using as little as 1% of the labeled data.

We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulated human skeleton motion as well as medium-scale non-rigid surface deformations in general scenes. Human performance capture is a challenging problem due to the large range of articulation, potentially fast motion, and considerable non-rigid deformations, even from multi-view data. Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem. We tackle these challenges by a novel approach that employs sparse 2D and 3D human pose detections from a convolutional neural network using a batch-based pose estimation strategy. Joint recovery of per-batch motion allows us to resolve the ambiguities of the monocular reconstruction problem based on a low-dimensional trajectory subspace. In addition, we propose refinement of the surface geometry based on fully automatically extracted silhouettes to enable medium-scale non-rigid alignment. We demonstrate state-of-the-art performance capture results that enable exciting applications such as video editing and free viewpoint video, previously infeasible from monocular video. Our qualitative and quantitative evaluation demonstrates that our approach significantly outperforms previous monocular methods in terms of accuracy, robustness, and scene complexity that can be handled.

We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data. Using only the existing 3D pose data and 2D pose data, we show state-of-the-art performance on established benchmarks through transfer of learned features, while also generalizing to in-the-wild scenes. We further introduce a new training set for human body pose estimation from monocular images of real humans that has the ground truth captured with a multi-camera marker-less motion capture system. It complements existing corpora with greater diversity in pose, human appearance, clothing, occlusion, and viewpoints, and enables an increased scope of augmentation. We also contribute a new benchmark that covers outdoor and indoor scenes, and demonstrate that our 3D pose dataset shows better in-the-wild performance than existing annotated data, which is further improved in conjunction with transfer learning from 2D pose data. All in all, we argue that the use of transfer learning of representations in tandem with algorithmic and data contributions is crucial for general 3D body pose estimation.

We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combines a new convolutional neural network (CNN) based pose regressor with kinematic skeleton fitting. Our novel fully-convolutional pose formulation regresses 2D and 3D joint positions jointly in real time and does not require tightly cropped input frames. A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton. This makes our approach the first monocular RGB method usable in real-time applications such as 3D character control---thus far, the only monocular methods for such applications employed specialized RGB-D cameras. Our method's accuracy is quantitatively on par with the best offline 3D monocular RGB pose estimation methods. Our results are qualitatively comparable to, and sometimes better than, results from monocular RGB-D approaches, such as the Kinect. However, we show that our approach is more broadly applicable than RGB-D solutions, i.e., it works for outdoor scenes, community videos, and low quality commodity RGB cameras.

We propose a new model-based method to accurately reconstruct human performances captured outdoors in a multi-camera setup. Starting from a template of the actor model, we introduce a new unified implicit representation for both, articulated skeleton tracking and non-rigid surface shape refinement. Our method fits the template to unsegmented video frames in two stages - first, the coarse skeletal pose is estimated, and subsequently non-rigid surface shape and body pose are jointly refined. Particularly for surface shape refinement we propose a new combination of 3D Gaussians designed to align the projected model with likely silhouette contours without explicit segmentation or edge detection. We obtain reconstructions of much higher quality in outdoor settings than existing methods, and show that we are on par with state-of-the-art methods on indoor scenes for which they were designed.

Marker-based and marker-less optical skeletal motion-capture methods use an outside-in arrangement of cameras placed around a scene, with viewpoints converging on the center. They often create discomfort with marker suits, and their recording volume is severely restricted and often constrained to indoor scenes with controlled backgrounds. Alternative suit-based systems use several inertial measurement units or an exoskeleton to capture motion with an inside-in setup, i.e. without external sensors. This makes capture independent of a confined volume, but requires substantial, often constraining, and hard to set up body instrumentation. Therefore, we propose a new method for real-time, marker-less, and egocentric motion capture: estimating the full-body skeleton pose from a lightweight stereo pair of fisheye cameras attached to a helmet or virtual reality headset - an optical inside-in method, so to speak. This allows full-body motion capture in general indoor and outdoor scenes, including crowded scenes with many people nearby, which enables reconstruction in larger-scale activities. Our approach combines the strength of a new generative pose estimation framework for fisheye views with a ConvNet-based body-part detector trained on a large new dataset. It is particularly useful in virtual reality to freely roam and interact, while seeing the fully motion-captured virtual body.

Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the visibility function that indicates if a surface point is seen from a camera can often not be formulated in closed form, and is in general discrete and non-differentiable at occlusion boundaries. We present a new scene representation that enables an analytically differentiable closed-form formulation of surface visibility. In contrast to previous methods, this yields smooth, analytically differentiable, and efficient to optimize pose similarity energies with rigorous occlusion handling, fewer local minima, and experimentally verified improved convergence of numerical optimization. The underlying idea is a new image formation model that represents opaque objects by a translucent medium with a smooth Gaussian density distribution which turns visibility into a smooth phenomenon. We demonstrate the advantages of our versatile scene model in several generative pose estimation problems, namely marker-less multi-object pose estimation, marker-less human motion capture with few cameras, and image-based 3D geometry estimation.

Motion-tracked real-time character control is important for games and VR, but current solutions are limited: retargeting is hard for non-human characters, with locomotion bound to the sensing volume; and pose mappings are ambiguous with difficult dynamic motion control. We robustly estimate wave properties --- amplitude, frequency, and phase ---for a set of interactively-defined gestures by mapping user motions to a low-dimensional independent representation. The mapping separates simultaneous or intersecting gestures, and extrapolates gesture variations from single training examples. For animations such as locomotion, wave properties map naturally to stride length, step frequency, and progression, and allow smooth transitions from standing, to walking, to running. Interpolating out-of-phase locomotions is hard, e.g., quadruped legs between walks and runs switch phase, so we introduce a new time-interpolation scheme to reduce artifacts. These improvements to real-time motion-tracked character control are important for common cyclic animations. We validate this in a user study, and show versatility to apply to part- and full-body motions across a variety of sensors.

Real-time marker-less hand tracking is of increasing importance in human-computer interaction. Robust and accurate tracking of arbitrary hand motion is a challenging problem due to the many degrees of freedom, frequent self-occlusions, fast motions, and uniform skin color. In this paper, we propose a new approach that tracks the full skeleton motion of the hand from multiple RGB cameras in real-time. The main contributions include a new generative tracking method which employs an implicit hand shape representation based on Sum of Anisotropic Gaussians (SAG), and a pose fitting energy that is smooth and analytically differentiable making fast gradient based pose optimization possible. This shape representation, together with a full perspective projection model, enables more accurate hand modeling than a related baseline method from literature. Our method achieves better accuracy than previous methods and runs at 25 fps. We show these improvements both qualitatively and quantitatively on publicly available datasets.

Abstract It is now possible to capture the 3D motion of the human body on consumer hardware and to puppet in real time skeleton‐based virtual characters. However, many characters do not have humanoid skeletons. Characters such as spiders and caterpillars do not have boned skeletons at all, and these characters have very different shapes and motions. In general, character control under arbitrary shape and motion transformations is unsolved ‐ how might these motions be mapped? We control characters with a method which avoids the rigging‐skinning pipeline — source and target characters do not have skeletons or rigs. We use interactively‐defined sparse pose correspondences to learn a mapping between arbitrary 3D point source sequences and mesh target sequences. Then, we puppet the target character in real time. We demonstrate the versatility of our method through results on diverse virtual characters with different input motion controllers. Our method provides a fast, flexible, and intuitive interface for arbitrary motion mapping which provides new ways to control characters for real‐time animation.