We present Vid2Avatar-Pro, a method to create photorealistic and animatable 3D human avatars from monocular in-the-wild videos. Building a high-quality avatar that supports animation with diverse poses from a monocular video is challenging because the observation of pose diversity and view points is inherently limited. The lack of pose variations typically leads to poor generalization to novel poses, and avatars can easily overfit to limited input view points, producing artifacts and distortions from other views. In this work, we address these limitations by leveraging a universal prior model (UPM) learned from a large corpus of multi-view clothed human performance capture data. We build our representation on top of expressive 3D Gaussians with canonical front and back maps shared across identities. Once the UPM is learned to accurately reproduce the large-scale multi-view human images, we fine-tune the model with an in-the-wild video via inverse rendering to obtain a personalized photorealistic human avatar that can be faithfully animated to novel human motions and rendered from novel views. The experiments show that our approach based on the learned universal prior sets a new state-of-the-art in monocular avatar reconstruction by substantially outperforming existing approaches relying only on heuristic regularization or a shape prior of minimally clothed bodies (e.g., SMPL) on publicly available datasets.

We present a novel method for reconstructing personalized 3D human avatars with realistic animation from only a few images. Due to the large variations in body shapes, poses, and cloth types, existing methods mostly require hours of per-subject optimization during inference, which limits their practical applications. In contrast, we learn a universal prior from over a thousand clothed humans to achieve instant feedforward generation and zero-shot generalization. Specifically, instead of rigging the avatar with shared skinning weights, we jointly infer personalized avatar shape, skinning weights, and pose-dependent deformations, which effectively improves overall geometric fidelity and reduces deformation artifacts. Moreover, to normalize pose variations and resolve coupled ambiguity between canonical shapes and skinning weights, we design a 3D canonicalization process to produce pixel-aligned initial conditions, which helps to reconstruct fine-grained geometric details. We then propose a multi-frame feature aggregation to robustly reduce artifacts introduced in canonicalization and fuse a plausible avatar preserving person-specific identities. Finally, we train the model in an end-to-end framework on a large-scale capture dataset, which contains diverse human subjects paired with high-quality 3D scans. Extensive experiments show that our method generates more authentic reconstruction and animation than state-of-the- arts, and can be directly generalized to inputs from casually taken phone photos. Project page and code is available at https://github.com/rongakowang/FRESA.

Existing photorealistic relightable hand models require extensive identity-specific observations in different views, poses, and illuminations, and face challenges in generalizing to natural illuminations and novel identities. To bridge this gap, we present URHand, the first universal relightable hand model that generalizes across viewpoints, poses, illuminations, and identities. Our model allows few-shot personalization using images captured with a mobile phone, and is ready to be photorealistically rendered under novel illuminations. To simplify the personalization process while retaining photorealism, we build a powerful universal relightable prior based on neural relighting from multi-view images of hands captured in a light stage with hundreds of identities. The key challenge is scaling the cross-identity training while maintaining personalized fidelity and sharp details without compromising generalization under natural illuminations. To this end, we propose a spatially varying linear lighting model as the neural renderer that takes physics-inspired shading as input feature. By removing non-linear activations and bias, our specifically designed lighting model explicitly keeps the linearity of light transport. This enables single-stage training from light-stage data while generalizing to real-time rendering under arbitrary continuous illuminations across diverse identities. In addition, we introduce the joint learning of a physically based model and our neural relighting model, which further improves fidelity and generalization. Extensive experiments show that our approach achieves superior performance over existing methods in terms of both quality and generalizability. We also demonstrate quick personalization of URHand from a short phone scan of an unseen identity.

3D calling – the ability to virtually share a 3D space with other people – has the potential to bring billions of people into artificial reality (AR/MR/VR). It is the next step in the evolution of telecommunication, from telegraphy to telephony to videoconferencing. In this talk, I will describe first steps towards achieving 3D calling that is indistinguishable from real-life interactions with avatars that look like you, move like you, and sound like you. If successful, 3D calling will produce the foundation for the next generation of algorithms and computing platforms for understanding social interactions. I will introduce codec avatars: the use of neural networks to unify the problems of understanding human behavior and rendering it. The creation of codec avatars requires capture systems of unprecedented resolution for the 3D sensing of social interactions, which I will also describe.

To build photorealistic avatars that users can embody, human modelling must be complete (cover the full body), driveable (able to reproduce the current motion and appearance from the user), and generalizable (i.e., easily adaptable to novel identities).Towards these goals, paired captures, that is, captures of the same subject obtained from systems of diverse quality and availability, are crucial.However, paired captures are rarely available to researchers outside of dedicated industrial labs: Codec Avatar Studio is our proposal to close this gap.Towards generalization and driveability, we introduce a dataset of 256 subjects captured in two modalities: high resolution multi-view scans of their heads, and video from the internal cameras of a headset.Towards completeness, we introduce a dataset of 4 subjects captured in eight modalities: high quality relightable multi-view captures of heads and hands, full body multi-view captures with minimal and regular clothes, and corresponding head, hands and body phone captures.Together with our data, we also provide code and pre-trained models for different state-of-the-art human generation models.Our datasets and code are available at https://github.com/facebookresearch/ava-256 and https://github.com/facebookresearch/goliath.

Faithful real-time facial animation is essential for avatar-mediated telepresence in Virtual Reality (VR). To emulate authentic communication, avatar animation needs to be efficient and accurate: able to capture both extreme and subtle expressions within a few milliseconds to sustain the rhythm of natural conversations. The oblique and incomplete views of the face, variability in the donning of headsets, and illumination variation due to the environment are some of the unique challenges in generalization to unseen faces. In this paper, we present a method that can animate a photorealistic avatar in realtime from head-mounted cameras (HMCs) on a consumer VR headset. We present a self-supervised learning approach, based on a cross-view reconstruction objective, that enables generalization to unseen users. We present a lightweight expression calibration mechanism that increases accuracy with minimal additional cost to run-time efficiency. We present an improved parameterization for precise ground-truth generation that provides robustness to environmental variation. The resulting system produces accurate facial animation for unseen users wearing VR headsets in realtime. We compare our approach to prior face-encoding methods demonstrating significant improvements in both quantitative metrics and qualitative results.

We present the first neural relighting approach for rendering high-fidelity personalized hands that can be animated in real-time under novel illumination. Our approach adopts a teacher-student framework, where the teacher learns appearance under a single point light from images captured in a light-stage, allowing us to synthesize hands in arbitrary illuminations but with heavy compute. Using images rendered by the teacher model as training data, an efficient student model directly predicts appearance under natural illuminations in real-time. To achieve generalization, we condition the student model with physics-inspired illumination features such as visibility, diffuse shading, and specular reflections computed on a coarse proxy geometry, maintaining a small computational overhead. Our key insight is that these features have strong correlation with subsequent global light transport effects, which proves sufficient as conditioning data for the neural relighting network. Moreover, in contrast to bottleneck illumination conditioning, these features are spatially aligned based on underlying geometry, leading to better generalization to unseen illuminations and poses. In our experiments, we demonstrate the efficacy of our illumination feature representations, outperforming baseline approaches. We also show that our approach can photorealistically relight two interacting hands at real-time speeds. https://sh8.io/#/relightable_hands

Bundle adjustment jointly optimizes camera intrinsics and extrinsics and 3D point triangulation to reconstruct a static scene. The triangulation constraint, however, is invalid for moving points captured in multiple unsynchronized videos and bundle adjustment is not designed to estimate the temporal alignment between cameras. We present a spatiotemporal bundle adjustment framework that jointly optimizes four coupled sub-problems: estimating camera intrinsics and extrinsics, triangulating static 3D points, as well as sub-frame temporal alignment between cameras and computing 3D trajectories of dynamic points. Key to our joint optimization is the careful integration of physics-based motion priors within the reconstruction pipeline, validated on a large motion capture corpus of human subjects. We devise an incremental reconstruction and alignment algorithm to strictly enforce the motion prior during the spatiotemporal bundle adjustment. This algorithm is further made more efficient by a divide and conquer scheme while still maintaining high accuracy. We apply this algorithm to reconstruct 3D motion trajectories of human bodies in dynamic events captured by multiple uncalibrated and unsynchronized video cameras in the wild. To make the reconstruction visually more interpretable, we fit a statistical 3D human body model to the asynchronous video streams. Compared to the baseline, the fitting significantly benefits from the proposed spatiotemporal bundle adjustment procedure. Because the videos are aligned with sub-frame precision, we reconstruct 3D motion at much higher temporal resolution than the input videos. Website: http://www.cs.cmu.edu/~ILIM/projects/IM/STBA.

Creating photorealistic avatars of existing people currently requires extensive person-specific data capture, which is usually only accessible to the VFX industry and not the general public. Our work aims to address this drawback by relying only on a short mobile phone capture to obtain a drivable 3D head avatar that matches a person's likeness faithfully. In contrast to existing approaches, our architecture avoids the complex task of directly modeling the entire manifold of human appearance, aiming instead to generate an avatar model that can be specialized to novel identities using only small amounts of data. The model dispenses with low-dimensional latent spaces that are commonly employed for hallucinating novel identities, and instead, uses a conditional representation that can extract person-specific information at multiple scales from a high resolution registered neutral phone scan. We achieve high quality results through the use of a novel universal avatar prior that has been trained on high resolution multi-view video captures of facial performances of hundreds of human subjects. By fine-tuning the model using inverse rendering we achieve increased realism and personalize its range of motion. The output of our approach is not only a high-fidelity 3D head avatar that matches the person's facial shape and appearance, but one that can also be driven using a jointly discovered shared global expression space with disentangled controls for gaze direction. Via a series of experiments we demonstrate that our avatars are faithful representations of the subject's likeness. Compared to other state-of-the-art methods for lightweight avatar creation, our approach exhibits superior visual quality and animateability.

We propose a novel multi-view camera pipeline for the reconstruction and registration of dynamic clothing. Our proposed method relies on a specifically designed pattern that allows for precise video tracking in each camera view. We triangulate the tracked points and register the cloth surface in a fine-grained geometric resolution and low localization error. Compared to state-of-the-art methods, our registration exhibits stable correspondence, tracking the same points on the deforming cloth surface along the temporal sequence. As an application, we demonstrate how the use of our registration pipeline greatly improves state-of-the-art pose-based drivable cloth models. Furthermore, we propose a novel model, Garment Avatar , for driving cloth from a dense tracking signal which is obtained from two opposing camera views. The method produces realistic reconstructions which are faithful to the actual geometry of the deforming cloth. In this setting, the user wears a garment with our custom pattern which enables our driving model to reconstruct the geometry. Our code and data are available at https://github.com/HalimiOshri/Pattern-Based-Cloth-Registration-and-Sparse-View-Animation. The released data includes our pattern and registered mesh sequences containing four different subjects and 15k frames in total.

Cameras with a finite aperture diameter exhibit defocus for scene elements that are not at the focus distance, and have only a limited depth of field within which objects appear acceptably sharp. In this work we address the problem of applying inverse rendering techniques to input data that exhibits such defocus blurring. We present differentiable depth-of-field rendering techniques that are applicable to both rasterization-based methods using mesh representations, as well as ray-marching-based methods using either explicit [Yu et al. 2021] or implicit volumetric radiance fields [Mildenhall et al. 2020]. Our approach learns significantly sharper scene reconstructions on data containing blur due to depth of field, and recovers aperture and focus distance parameters that result in plausible forward-rendered images. We show applications to macro photography, where typical lens configurations result in a very narrow depth of field, and to multi-camera video capture, where maintaining sharp focus across a large capture volume for a moving subject is difficult.

Despite recent progress in developing animatable full-body avatars, realistic modeling of clothing - one of the core aspects of human self-expression - remains an open challenge. State-of-the-art physical simulation methods can generate realistically behaving clothing geometry at interactive rates. Modeling photorealistic appearance, however, usually requires physically-based rendering which is too expensive for interactive applications. On the other hand, data-driven deep appearance models are capable of efficiently producing realistic appearance, but struggle at synthesizing geometry of highly dynamic clothing and handling challenging body-clothing configurations. To this end, we introduce pose-driven avatars with explicit modeling of clothing that exhibit both photorealistic appearance learned from real-world data and realistic clothing dynamics. The key idea is to introduce a neural clothing appearance model that operates on top of explicit geometry: at training time we use high-fidelity tracking, whereas at animation time we rely on physically simulated geometry. Our core contribution is a physically-inspired appearance network, capable of generating photorealistic appearance with view-dependent and dynamic shadowing effects even for unseen body-clothing configurations. We conduct a thorough evaluation of our model and demonstrate diverse animation results on several subjects and different types of clothing. Unlike previous work on photorealistic full-body avatars, our approach can produce much richer dynamics and more realistic deformations even for many examples of loose clothing. We also demonstrate that our formulation naturally allows clothing to be used with avatars of different people while staying fully animatable, thus enabling, for the first time, photorealistic avatars with novel clothing.

3D video avatars can empower virtual communications by providing compression, privacy, entertainment, and a sense of presence in AR/VR. Best 3D photo-realistic AR/VR avatars driven by video, that can minimize uncanny effects, rely on person-specific models. However, existing person-specific photo-realistic 3D models are not robust to lighting, hence their results typically miss subtle facial behaviors and cause artifacts in the avatar. This is a major drawback for the scalability of these models in communication systems (e.g., Messenger, Skype, FaceTime) and AR/VR. This paper addresses previous limitations by learning a deep learning lighting model, that in combination with a high-quality 3D face tracking algorithm, provides a method for subtle and robust facial motion transfer from a regular video to a 3D photo-realistic avatar. Extensive experimental validation and comparisons to other state-of-the-art methods demonstrate the effectiveness of the proposed framework in real-world scenarios with variability in pose, expression, and illumination. Our project page can be found at this website.

Estimation of accurate head-related transfer functions (HRTFs) is crucial to achieve realistic binaural acoustic experiences. HRTFs depend on source/listener locations and are therefore expensive and cumbersome to measure; traditional approaches require listener-dependent measurements of HRTFs at thousands of distinct spatial directions in an anechoic chamber. In this work, we present a data-driven approach to learn HRTFs implicitly with a neural network that achieves state of the art results compared to traditional approaches but relies on a much simpler data capture that can be performed in arbitrary, non-anechoic rooms. Despite that simpler and less acoustically ideal data capture, our deep learning based approach learns HRTF of high quality. We show in a perceptual study that the produced binaural audio is ranked on par with traditional DSP approaches by humans and illustrate that interaural time differences (ITDs), interaural level differences (ILDs) and spectral clues are accurately estimated.

This paper presents a generic method for generating full facial 3D animation from speech. Existing approaches to audio-driven facial animation exhibit uncanny or static upper face animation, fail to produce accurate and plausible co-articulation or rely on person-specific models that limit their scalability. To improve upon existing models, we propose a generic audio-driven facial animation approach that achieves highly realistic motion synthesis results for the entire face. At the core of our approach is a categorical latent space for facial animation that disentangles audio-correlated and audio-uncorrelated information based on a novel cross-modality loss. Our approach ensures highly accurate lip motion, while also synthesizing plausible animation of the parts of the face that are uncorrelated to the audio signal, such as eye blinks and eye brow motion. We demonstrate that our approach outperforms several baselines and obtains state-of-the-art quality both qualitatively and quantitatively. A perceptual user study demonstrates that our approach is deemed more realistic than the current state-of-the-art in over 75% of cases. We recommend watching the supplemental video before reading the paper: https://github.com/facebookresearch/meshtalk

Codec Avatars are a recent class of learned, photorealistic face models that accurately represent the geometry and texture of a person in 3D (i.e., for virtual reality), and are almost indistinguishable from video [28]. In this paper we describe the first approach to animate these parametric models in real-time which could be deployed on commodity virtual reality hardware using audio and/or eye tracking. Our goal is to display expressive conversations between individuals that exhibit important social signals such as laughter and excitement solely from la-tent cues in our lossy input signals. To this end we collected over 5 hours of high frame rate 3D face scans across three participants including traditional neutral speech as well as expressive and conversational speech. We investigate a multimodal fusion approach that dynamically identifies which sensor encoding should animate which parts of the face at any time. See the supplemental video which demonstrates our ability to generate full face motion far beyond the typically neutral lip articulations seen in competing work: https://research.fb.com/videos/audio-and-gaze-driven-facial-animation-of-codec-avatars/.

Realtime multi-person 2D pose estimation is a key component in enabling machines to have an understanding of people in images and videos. In this work, we present a realtime approach to detect the 2D pose of multiple people in an image. The proposed method uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. This bottom-up system achieves high accuracy and realtime performance, regardless of the number of people in the image. In previous work, PAFs and body part location estimation were refined simultaneously across training stages. We demonstrate that a PAF-only refinement rather than both PAF and body part location refinement results in a substantial increase in both runtime performance and accuracy. We also present the first combined body and foot keypoint detector, based on an internal annotated foot dataset that we have publicly released. We show that the combined detector not only reduces the inference time compared to running them sequentially, but also maintains the accuracy of each component individually. This work has culminated in the release of OpenPose, the first open-source realtime system for multi-person 2D pose detection, including body, foot, hand, and facial keypoints.

We present supervision by registration and triangulation (SRT), an unsupervised approach that utilizes unlabeled multi-view video to improve the accuracy and precision of landmark detectors. Being able to utilize unlabeled data enables our detectors to learn from massive amounts of unlabeled data freely available and not be limited by the quality and quantity of manual human annotations. To utilize unlabeled data, there are two key observations: (I) The detections of the same landmark in adjacent frames should be coherent with registration, i.e., optical flow. (II) The detections of the same landmark in multiple synchronized and geometrically calibrated views should correspond to a single 3D point, i.e., multi-view consistency. Registration and multi-view consistency are sources of supervision that do not require manual labeling, thus it can be leveraged to augment existing training data during detector training. End-to-end training is made possible by differentiable registration and 3D triangulation modules. Experiments with 11 datasets and a newly proposed metric to measure precision demonstrate accuracy and precision improvements in landmark detection on both images and video.

Reliable markerless motion tracking of people participating in a complex group activity from multiple moving cameras is challenging due to frequent occlusions, strong viewpoint and appearance variations, and asynchronous video streams. To solve this problem, reliable association of the same person across distant viewpoints and temporal instances is essential. We present a self-supervised framework to adapt a generic person appearance descriptor to the unlabeled videos by exploiting motion tracking, mutual exclusion constraints, and multi-view geometry. The adapted discriminative descriptor is used in a tracking-by-clustering formulation. We validate the effectiveness of our descriptor learning on WILDTRACK T. Chavdarova et al., "WILDTRACK: A multi-camera HD dataset for dense unscripted pedestrian detection," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 5030-5039. and three new complex social scenes captured by multiple cameras with up to 60 people "in the wild". We report significant improvement in association accuracy (up to 18 percent) and stable and coherent 3D human skeleton tracking (5 to 10 times) over the baseline. Using the reconstructed 3D skeletons, we cut the input videos into a multi-angle video where the image of a specified person is shown from the best visible front-facing camera. Our algorithm detects inter-human occlusion to determine the camera switching moment while still maintaining the flow of the action well. Website: http://www.cs.cmu.edu/~ILIM/projects/IM/Association4Tracking.

We present a learning-based method for building driving-signal aware full-body avatars. Our model is a conditional variational autoencoder that can be animated with incomplete driving signals, such as human pose and facial keypoints, and produces a high-quality representation of human geometry and view-dependent appearance. The core intuition behind our method is that better drivability and generalization can be achieved by disentangling the driving signals and remaining generative factors, which are not available during animation. To this end, we explicitly account for information deficiency in the driving signal by introducing a latent space that exclusively captures the remaining information, thus enabling the imputation of the missing factors required during full-body animation, while remaining faithful to the driving signal. We also propose a learnable localized compression for the driving signal which promotes better generalization, and helps minimize the influence of global chance-correlations often found in real datasets. For a given driving signal, the resulting variational model produces a compact space of uncertainty for missing factors that allows for an imputation strategy best suited to a particular application. We demonstrate the efficacy of our approach on the challenging problem of full-body animation for virtual telepresence with driving signals acquired from minimal sensors placed in the environment and mounted on a VR-headset.

We present a method for building high-fidelity animatable 3D face models that can be posed and rendered with novel lighting environments in real-time. Our main insight is that relightable models trained to produce an image lit from a single light direction can generalize to natural illumination conditions but are computationally expensive to render. On the other hand, efficient, high-fidelity face models trained with point-light data do not generalize to novel lighting conditions. We leverage the strengths of each of these two approaches. We first train an expensive but generalizable model on point-light illuminations, and use it to generate a training set of high-quality synthetic face images under natural illumination conditions. We then train an efficient model on this augmented dataset, reducing the generalization ability requirements. As the efficacy of this approach hinges on the quality of the synthetic data we can generate, we present a study of lighting pattern combinations for dynamic captures and evaluate their suitability for learning generalizable relightable models. Towards achieving the best possible quality, we present a novel approach for generating dynamic relightable faces that exceeds state-of-the-art performance. Our method is capable of capturing subtle lighting effects and can even generate compelling near-field relighting despite being trained exclusively with far-field lighting data. Finally, we motivate the utility of our model by animating it with images captured from VR-headset mounted cameras, demonstrating the first system for face-driven interactions in VR that uses a photorealistic relightable face model.

We present a method for performing real-time facial animation of a 3D avatar from binocular video. Existing facial animation methods fail to automatically capture precise and subtle facial motions for driving a photo-realistic 3D avatar "in-the-wild" (i.e., variability in illumination, camera noise). The novelty of our approach lies in a light-weight process for specializing a personalized face model to new environments that enables extremely accurate real-time face tracking anywhere. Our method uses a pre-trained high-fidelity personalized model of the face that we complement with a novel illumination model to account for variations due to lighting and other factors often encountered in-the-wild (e.g., facial hair growth, makeup, skin blemishes). Our approach comprises two steps. First, we solve for our illumination model's parameters by applying analysis-by-synthesis on a short video recording. Using the pairs of model parameters (rigid, non-rigid) and the original images, we learn a regression for real-time inference from the image space to the 3D shape and texture of the avatar. Second, given a new video, we fine-tune the real-time regression model with a few-shot learning strategy to adapt the regression model to the new environment. We demonstrate our system's ability to precisely capture subtle facial motions in unconstrained scenarios, in comparison to competing methods, on a diverse collection of identities, expressions, and real-world environments.

Real-time rendering and animation of humans is a core function in games, movies, and telepresence applications. Existing methods have a number of drawbacks we aim to address with our work. Triangle meshes have difficulty modeling thin structures like hair, volumetric representations like Neural Volumes are too low-resolution given a reasonable memory budget, and high-resolution implicit representations like Neural Radiance Fields are too slow for use in real-time applications. We present Mixture of Volumetric Primitives (MVP), a representation for rendering dynamic 3D content that combines the completeness of volumetric representations with the efficiency of primitive-based rendering, e.g., point-based or mesh-based methods. Our approach achieves this by leveraging spatially shared computation with a convolutional architecture and by minimizing computation in empty regions of space with volumetric primitives that can move to cover only occupied regions. Our parameterization supports the integration of correspondence and tracking constraints, while being robust to areas where classical tracking fails, such as around thin or translucent structures and areas with large topological variability. MVP is a hybrid that generalizes both volumetric and primitive-based representations. Through a series of extensive experiments we demonstrate that it inherits the strengths of each, while avoiding many of their limitations. We also compare our approach to several state-of-the-art methods and demonstrate that MVP produces superior results in terms of quality and runtime performance.

We present a data-driven approach for 4D space-time visualization of dynamic events from videos captured by hand-held multiple cameras. Key to our approach is the use of self-supervised neural networks specific to the scene to compose static and dynamic aspects of an event. Though captured from discrete viewpoints, this model enables us to move around the space-time of the event continuously. This model allows us to create virtual cameras that facilitate: (1) freezing the time and exploring views; (2) freezing a view and moving through time; and (3) simultaneously changing both time and view. We can also edit the videos and reveal occluded objects for a given view if it is visible in any of the other views. We validate our approach on challenging in-the-wild events captured using up to 15 mobile cameras.

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to capture fine-grained deformations. Furthermore, these methods can only be applied to a template-specific surface mesh, and is not applicable to more general meshes, like tetrahedrons and non-manifold meshes. While more general graph convolution methods can be employed, they lack performance in reconstruction precision and require higher memory usage. In this paper, we propose a non-template-specific fully convolutional mesh autoencoder for arbitrary registered mesh data. It is enabled by our novel convolution and (un)pooling operators learned with globally shared weights and locally varying coefficients which can efficiently capture the spatially varying contents presented by irregular mesh connections. Our model outperforms state-of-the-art methods on reconstruction accuracy. In addition, the latent codes of our network are fully localized thanks to the fully convolutional structure, and thus have much higher interpolation capability than many traditional 3D mesh generation models.

Interacting with people across large distances is important for remote work, interpersonal relationships, and entertainment. While such face-to-face interactions can be achieved using 2D video conferencing or, more recently, virtual reality (VR), telepresence systems currently distort the communication of eye contact and social gaze signals. Although methods have been proposed to redirect gaze in 2D teleconferencing situations to enable eye contact, 2D video conferencing lacks the 3D immersion of real life. To address these problems, we develop a system for face-to-face interaction in VR that focuses on reproducing photorealistic gaze and eye contact. To do this, we create a 3D virtual avatar model that can be animated by cameras mounted on a VR headset to accurately track and reproduce human gaze in VR. Our primary contributions in this work are a jointly-learnable 3D face and eyeball model that better represents gaze direction and upper facial expressions, a method for disentangling the gaze of the left and right eyes from each other and the rest of the face allowing the model to represent entirely unseen combinations of gaze and expression, and a gaze-aware model for precise animation from headset-mounted cameras. Our quantitative experiments show that our method results in higher reconstruction quality, and qualitative results show our method gives a greatly improved sense of presence for VR avatars.

Many of the actions that we take with our hands involve self-contact and occlusion: shaking hands, making a fist, or interlacing our fingers while thinking. This use of of our hands illustrates the importance of tracking hands through self-contact and occlusion for many applications in computer vision and graphics, but existing methods for tracking hands and faces are not designed to treat the extreme amounts of self-contact and self-occlusion exhibited by common hand gestures. By extending recent advances in vision-based tracking and physically based animation, we present the first algorithm capable of tracking high-fidelity hand deformations through highly self-contacting and self-occluding hand gestures, for both single hands and two hands. By constraining a vision-based tracking algorithm with a physically based deformable model, we obtain an algorithm that is robust to the ubiquitous self-interactions and massive self-occlusions exhibited by common hand gestures, allowing us to track two hand interactions and some of the most difficult possible configurations of a human hand.

We introduce a data-driven model for interactively synthesizing in-the-wild images from semantic label input masks. Our approach is dramatically different from recent work in this space, in that we make use of no learning. Instead, our approach uses simple but classic tools for matching scene context, shapes, and parts to a stored library of exemplars. Though simple, this approach has several notable advantages over recent work: (1) because nothing is learned, it is not limited to specific training data distributions (such as cityscapes, facades, or faces); (2) it can synthesize arbitrarily high-resolution images, limited only by the resolution of the exemplar library; (3) by appropriately composing shapes and parts, it can generate an exponentially large set of viable candidate output images (that can say, be interactively searched by a user). We present results on the diverse COCO dataset, significantly outperforming learning-based approaches on standard image synthesis metrics. Finally, we explore user-interaction and user-controllability, demonstrating that our system can be used as a platform for user-driven content creation.

We present a new research task and a dataset to understand human social interactions via computational methods, to ultimately endow machines with the ability to encode and decode a broad channel of social signals humans use. This research direction is essential to make a machine that genuinely communicates with humans, which we call Social Artificial Intelligence. We first formulate the "social signal prediction'' problem as a way to model the dynamics of social signals exchanged among interacting individuals in a data-driven way. We then present a new 3D motion capture dataset to explore this problem, where the broad spectrum of social signals (3D body, face, and hand motions) are captured in a triadic social interaction scenario. Baseline approaches to predict speaking status, social formation, and body gestures of interacting individuals are presented in the defined social prediction framework.

We present LBS-AE; a self-supervised autoencoding algorithm for fitting articulated mesh models to point clouds. As input, we take a sequence of point clouds to be registered as well as an artist-rigged mesh, i.e. a template mesh equipped with a linear-blend skinning (LBS) deformation space parameterized by a skeleton hierarchy. As output, we learn an LBS-based autoencoder that produces registered meshes from the input point clouds. To bridge the gap between the artist-defined geometry and the captured point clouds, our autoencoder models pose-dependent deviations from the template geometry. During training, instead of us- ing explicit correspondences, such as key points or pose supervision, our method leverages LBS deformations to boot- strap the learning process. To avoid poor local minima from erroneous point-to-point correspondences, we utilize a structured Chamfer distance based on part-segmentations, which are learned concurrently using self-supervision. We demonstrate qualitative results on real captured hands, and report quantitative evaluations on the FAUST benchmark for body registration. Our method achieves performance that is superior to other unsupervised approaches and com- parable to methods using supervised examples.

Hair is one of the most challenging objects to reconstruct due to its micro-scale structure and a large number of repeated strands with heavy occlusions. In this paper, we present the first method to capture high-fidelity hair geometry with strand-level accuracy. Our method takes three stages to achieve this. In the first stage, a new multi-view stereo method with a slanted support line is proposed to solve the hair correspondences between different views. In detail, we contribute a novel cost function consisting of both photo-consistency term and geometric term that reconstructs each hair pixel as a 3D line. By merging all the depth maps, a point cloud, as well as local line directions for each point, is obtained. Thus, in the second stage, we feature a novel strand reconstruction method with the mean-shift to convert the noisy point data to a set of strands. Lastly, we grow the hair strands with multi-view geometric constraints to elongate the short strands and recover the missing strands, thus significantly increasing the reconstruction completeness. We evaluate our method on both synthetic data and real captured data, showing that our method can reconstruct hair strands with sub-millimeter accuracy.

We present an online approach to efficiently and simultaneously detect and track 2D poses of multiple people in a video sequence. We build upon Part Affinity Field (PAF) representation designed for static images, and propose an architecture that can encode and predict Spatio-Temporal Affinity Fields (STAF) across a video sequence. In particular, we propose a novel temporal topology cross-linked across limbs which can consistently handle body motions of a wide range of magnitudes. Additionally, we make the overall approach recurrent in nature, where the network ingests STAF heatmaps from previous frames and estimates those for the current frame. Our approach uses only online inference and tracking, and is currently the fastest and the most accurate bottom-up approach that is runtime-invariant to the number of people in the scene and accuracy-invariant to input frame rate of camera. Running at ~30 fps on a single GPU at single scale, it achieves highly competitive results on the PoseTrack benchmarks.

We present the first method to capture the 3D total motion of a target person from a monocular view input. Given an image or a monocular video, our method reconstructs the motion from body, face, and fingers represented by a 3D deformable mesh model. We use an efficient representation called 3D Part Orientation Fields (POFs), to encode the 3D orientations of all body parts in the common 2D image space. POFs are predicted by a Fully Convolutional Network, along with the joint confidence maps. To train our network, we collect a new 3D human motion dataset capturing diverse total body motion of 40 subjects in a multiview system. We leverage a 3D deformable human model to reconstruct total body pose from the CNN outputs with the aid of the pose and shape prior in the model. We also present a texture-based tracking method to obtain temporally coherent motion capture output. We perform thorough quantitative evaluations including comparison with the existing body-specific and hand-specific methods, and performance analysis on camera viewpoint and human pose changes. Finally, we demonstrate the results of our total body motion capture on various challenging in-the-wild videos.

We present a 16.2-million frame (50-hour) multimodal dataset of two-person face-to-face spontaneous conversations. Our dataset features synchronized body and finger motion as well as audio data. To the best of our knowledge, it represents the largest motion capture and audio dataset of natural conversations to date. The statistical analysis verifies strong intraperson and interperson covariance of arm, hand, and speech features, potentially enabling new directions on data-driven social behavior analysis, prediction, and synthesis. As an illustration, we propose a novel real-time finger motion synthesis method: a temporal neural network innovatively trained with an inverse kinematics (IK) loss, which adds skeletal structural information to the generative model. Our qualitative user study shows that the finger motion generated by our method is perceived as natural and conversation enhancing, while the quantitative ablation study demonstrates the effectiveness of IK loss.

We present the first single-network approach for 2D~whole-body pose estimation, which entails simultaneous localization of body, face, hands, and feet keypoints. Due to the bottom-up formulation, our method maintains constant real-time performance regardless of the number of people in the image. The network is trained in a single stage using multi-task learning, through an improved architecture which can handle scale differences between body/foot and face/hand keypoints. Our approach considerably improves upon OpenPose~\cite{cao2018openpose}, the only work so far capable of whole-body pose estimation, both in terms of speed and global accuracy. Unlike OpenPose, our method does not need to run an additional network for each hand and face candidate, making it substantially faster for multi-person scenarios. This work directly results in a reduction of computational complexity for applications that require 2D whole-body information (e.g., VR/AR, re-targeting). In addition, it yields higher accuracy, especially for occluded, blurry, and low resolution faces and hands. For code, trained models, and validation benchmarks, visit our project page: https://github.com/CMU-Perceptual-Computing-Lab/openpose_train.

Non verbal behaviours such as gestures, facial expressions, body posture, and para-linguistic cues have been shown to complement or clarify verbal messages. Hence to improve telepresence, in form of an avatar, it is important to model these behaviours, especially in dyadic interactions. Creating such personalized avatars not only requires to model intrapersonal dynamics between a avatar’s speech and their body pose, but it also needs to model interpersonal dynamics with the interlocutor present in the conversation. In this paper, we introduce a neural architecture named Dyadic Residual-Attention Model (DRAM), which integrates intrapersonal (monadic) and interpersonal (dyadic) dynamics using selective attention to generate sequences of body pose conditioned on audio and body pose of the interlocutor and audio of the human operating the avatar. We evaluate our proposed model on dyadic conversational data consisting of pose and audio of both participants, confirming the importance of adaptive attention between monadic and dyadic dynamics when predicting avatar pose. We also conduct a user study to analyze judgments of human observers. Our results confirm that the generated body pose is more natural, models intrapersonal dynamics and interpersonal dynamics better than non-adaptive monadic/dyadic models.

We present an approach to capture the 3D motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is functional and frequent; (2) subtle motion needs to be measured over a space large enough to host a social group; (3) human appearance and configuration variation is immense; and (4) attaching markers to the body may prime the nature of interactions. The Panoptic Studio is a system organized around the thesis that social interactions should be measured through the integration of perceptual analyses over a large variety of view points. We present a modularized system designed around this principle, consisting of integrated structural, hardware, and software innovations. The system takes, as input, 480 synchronized video streams of multiple people engaged in social activities, and produces, as output, the labeled time-varying 3D structure of anatomical landmarks on individuals in the space. Our algorithm is designed to fuse the "weak" perceptual processes in the large number of views by progressively generating skeletal proposals from low-level appearance cues, and a framework for temporal refinement is also presented by associating body parts to reconstructed dense 3D trajectory stream. Our system and method are the first in reconstructing full body motion of more than five people engaged in social interactions without using markers. We also empirically demonstrate the impact of the number of views in achieving this goal.

Modeling and rendering of dynamic scenes is challenging, as natural scenes often contain complex phenomena such as thin structures, evolving topology, translucency, scattering, occlusion, and biological motion. Mesh-based reconstruction and tracking often fail in these cases, and other approaches (e.g., light field video) typically rely on constrained viewing conditions, which limit interactivity. We circumvent these difficulties by presenting a learning-based approach to representing dynamic objects inspired by the integral projection model used in tomographic imaging. The approach is supervised directly from 2D images in a multi-view capture setting and does not require explicit reconstruction or tracking of the object. Our method has two primary components: an encoder-decoder network that transforms input images into a 3D volume representation, and a differentiable ray-marching operation that enables end-to-end training. By virtue of its 3D representation, our construction extrapolates better to novel viewpoints compared to screen-space rendering techniques. The encoder-decoder architecture learns a latent representation of a dynamic scene that enables us to produce novel content sequences not seen during training. To overcome memory limitations of voxel-based representations, we learn a dynamic irregular grid structure implemented with a warp field during ray-marching. This structure greatly improves the apparent resolution and reduces grid-like artifacts and jagged motion. Finally, we demonstrate how to incorporate surface-based representations into our volumetric-learning framework for applications where the highest resolution is required, using facial performance capture as a case in point.

A key promise of Virtual Reality (VR) is the possibility of remote social interaction that is more immersive than any prior telecommunication media. However, existing social VR experiences are mediated by inauthentic digital representations of the user (i.e., stylized avatars). These stylized representations have limited the adoption of social VR applications in precisely those cases where immersion is most necessary (e.g., professional interactions and intimate conversations). In this work, we present a bidirectional system that can animate avatar heads of both users' full likeness using consumer-friendly headset mounted cameras (HMC). There are two main challenges in doing this: unaccommodating camera views and the image-to-avatar domain gap. We address both challenges by leveraging constraints imposed by multiview geometry to establish precise image-to-avatar correspondence, which are then used to learn an end-to-end model for real-time tracking. We present designs for a training HMC, aimed at data-collection and model building, and a tracking HMC for use during interactions in VR. Correspondence between the avatar and the HMC-acquired images are automatically found through self-supervised multiview image translation, which does not require manual annotation or one-to-one correspondence between domains. We evaluate the system on a variety of users and demonstrate significant improvements over prior work.

We propose a method for learning non-linear face geometry representations using deep generative models. Our model is a variational autoencoder with multiple levels of hidden variables where lower layers capture global geometry and higher ones encode more local deformations. Based on that, we propose a new parameterization of facial geometry that naturally decomposes the structure of the human face into a set of semantically meaningful levels of detail. This parameterization enables us to do model fitting while capturing varying level of detail under different types of geometrical constraints.

In this paper, we present supervision-by-registration, an unsupervised approach to improve the precision of facial landmark detectors on both images and video. Our key observation is that the detections of the same landmark in adjacent frames should be coherent with registration, i.e., optical flow. Interestingly, coherency of optical flow is a source of supervision that does not require manual labeling, and can be leveraged during detector training. For example, we can enforce in the training loss function that a detected landmark at framet-1followed by optical flow tracking from framet-1to frametshould coincide with the location of the detection at framet. Essentially, supervision-by-registration augments the training loss function with a registration loss, thus training the detector to have output that is not only close to the annotations in labeled images, but also consistent with registration on large amounts of unlabeled videos. End-to-end training with the registration loss is made possible by a differentiable Lucas-Kanade operation, which computes optical flow registration in the forward pass, and back-propagates gradients that encourage temporal coherency in the detector. The output of our method is a more precise image-based facial landmark detector, which can be applied to single images or video. With supervision-by-registration, we demonstrate (1) improvements in facial landmark detection on both images (300W, ALFW) and video (300VW, Youtube-Celebrities), and (2) significant reduction of jittering in video detections.

The following topics are dealt with: learning (artificial intelligence); feature extraction; image classification; neural nets; image representation; object detection; image segmentation; convolution; feedforward neural nets; video signal processing.

This paper proposes a new method for Non-Rigid Structure-from-Motion (NRSfM) from a long monocular video sequence observing a non-rigid object performing recurrent and possibly repetitive dynamic action. Departing from the traditional idea of using linear low-order or low-rank shape model for the task of NRSfM, our method exploits the property of shape recurrency (i.e., many deforming shapes tend to repeat themselves in time). We show that recurrency is in fact a generalized rigidity. Based on this, we reduce NRSfM problems to rigid ones provided that certain recurrency condition is satisfied. Given such a reduction, standard rigid-SfM techniques are directly applicable (without any change) to the reconstruction of non-rigid dynamic shapes. To implement this idea as a practical approach, this paper develops efficient algorithms for automatic recurrency detection, as well as camera view clustering via a rigidity-check. Experiments on both simulated sequences and real data demonstrate the effectiveness of the method. Since this paper offers a novel perspective on rethinking structure-from-motion, we hope it will inspire other new problems in the field.

We present an approach to accelerate multi-view stereo (MVS) by prioritizing computation on image patches that are likely to produce accurate 3D surface reconstructions. Our key insight is that the accuracy of the surface reconstruction from a given image patch can be predicted significantly faster than performing the actual stereo matching. The intuition is that non-specular, fronto-parallel, in-focus patches are more likely to produce accurate surface reconstructions than highly specular, slanted, blurry patches - and that these properties can be reliably predicted from the image itself. By prioritizing stereo matching on a subset of patches that are highly reconstructable and also cover the 3D surface, we are able to accelerate MVS with minimal reduction in accuracy and completeness. To predict the reconstructability score of an image patch from a single view, we train an image-to-reconstructability neural network: the I2RNet. This reconstructability score enables us to efficiently identify image patches that are likely to provide the most accurate surface estimates before performing stereo matching. We demonstrate that the I2RNet, when trained on the ScanNet dataset, generalizes to the DTU and Tanks & Temples MVS datasets. By using our I2RNet with an existing MVS implementation, we show that our method can achieve more than a 30× speed-up over the baseline with only an minimal loss in completeness.

We introduce a deep appearance model for rendering the human face. Inspired by Active Appearance Models, we develop a data-driven rendering pipeline that learns a joint representation of facial geometry and appearance from a multiview capture setup. Vertex positions and view-specific textures are modeled using a deep variational autoencoder that captures complex nonlinear effects while producing a smooth and compact latent representation. View-specific texture enables the modeling of view-dependent effects such as specularity. In addition, it can also correct for imperfect geometry stemming from biased or low resolution estimates. This is a significant departure from the traditional graphics pipeline, which requires highly accurate geometry as well as all elements of the shading model to achieve realism through physically-inspired light transport. Acquiring such a high level of accuracy is difficult in practice, especially for complex and intricate parts of the face, such as eyelashes and the oral cavity. These are handled naturally by our approach, which does not rely on precise estimates of geometry. Instead, the shading model accommodates deficiencies in geometry though the flexibility afforded by the neural network employed. At inference time, we condition the decoding network on the viewpoint of the camera in order to generate the appropriate texture for rendering. The resulting system can be implemented simply using existing rendering engines through dynamic textures with flat lighting. This representation, together with a novel unsupervised technique for mapping images to facial states, results in a system that is naturally suited to real-time interactive settings such as Virtual Reality (VR).

In this paper, we present an incremental learning framework for efficient and accurate facial performance tracking. Our approach is to alternate the modeling step, which takes tracked meshes and texture maps to train our deep learning-based statistical model, and the tracking step, which takes predictions of geometry and texture our model infers from measured images and optimize the predicted geometry by minimizing image, geometry and facial landmark errors. Our Geo-Tex VAE model extends the convolutional variational autoencoder for face tracking, and jointly learns and represents deformations and variations in geometry and texture from tracked meshes and texture maps. To accurately model variations in facial geometry and texture, we introduce the decomposition layer in the Geo-Tex VAE architecture which decomposes the facial deformation into global and local components. We train the global deformation with a fully-connected network and the local deformations with convolutional layers. Despite running this model on each frame independently - thereby enabling a high amount of parallelization - we validate that our framework achieves sub-millimeter accuracy on synthetic data and outperforms existing methods. We also qualitatively demonstrate high-fidelity, long-duration facial performance tracking on several actors.

We present an approach to efficiently detect the 2D pose of multiple people in an image. The approach uses a nonparametric representation, which we refer to as Part Affinity Fields (PAFs), to learn to associate body parts with individuals in the image. The architecture encodes global context, allowing a greedy bottom-up parsing step that maintains high accuracy while achieving realtime performance, irrespective of the number of people in the image. The architecture is designed to jointly learn part locations and their association via two branches of the same sequential prediction process. Our method placed first in the inaugural COCO 2016 keypoints challenge, and significantly exceeds the previous state-of-the-art result on the MPII Multi-Person benchmark, both in performance and efficiency.

We present an approach that uses a multi-camera system to train fine-grained detectors for keypoints that are prone to occlusion, such as the joints of a hand. We call this procedure multiview bootstrapping: first, an initial keypoint detector is used to produce noisy labels in multiple views of the hand. The noisy detections are then triangulated in 3D using multiview geometry or marked as outliers. Finally, the reprojected triangulations are used as new labeled training data to improve the detector. We repeat this process, generating more labeled data in each iteration. We derive a result analytically relating the minimum number of views to achieve target true and false positive rates for a given detector. The method is used to train a hand keypoint detector for single images. The resulting keypoint detector runs in realtime on RGB images and has accuracy comparable to methods that use depth sensors. The single view detector, triangulated over multiple views, enables 3D markerless hand motion capture with complex object interactions.

The recent proliferation of high resolution cameras presents an opportunity to achieve unprecedented levels of precision in visual 3D reconstruction. Yet the camera calibration pipeline, developed decades ago using checkerboards, has remained the de facto standard. In this paper, we ask the question: are checkerboards the optimal pattern for high precision calibration? We empirically demonstrate that deltille grids (regular triangular tiling) produce the highest precision calibration of the possible tilings of Euclidean plane. We posit that they should be the new standard for high-precision calibration and present a complete ecosystem for calibration using deltille grids including: (1) a highly precise corner detection algorithm based on polynomial surface fitting; (2) an indexing scheme based on polarities extracted from the fitted surfaces; and (3) a 2D coding system for deltille grids, which we refer to as DelTags, in lieu of conventional matrix barcodes. We demonstrate state-of-the-art performance and apply the full calibration ecosystem through the use of 3D calibration objects for multiview camera calibration.

Recovering dynamic 3D structures from 2D image observations is highly under-constrained because of projection and missing data, motivating the use of strong priors to constrain shape deformation. In this paper, we empirically show that the spatiotemporal covariance of natural deformations is dominated by a Kronecker pattern. We demonstrate that this pattern arises as the limit of a spatiotemporal autoregressive process, and derive a Kronecker Markov Random Field as a prior distribution over dynamic structures. This distribution unifies shape and trajectory models of prior art and has the individual models as its marginals. The key assumption of the Kronecker MRF is that the spatiotemporal covariance is separable into the product of a temporal and a shape covariance, and can therefore be modeled using the matrix normal distribution. Analysis on motion capture data validates that this distribution is an accurate approximation with significantly fewer free parameters. Using the trace-norm, we present a convex method to estimate missing data from a single sequence when the marginal shape distribution is unknown. The Kronecker-Markov distribution, fit to a single sequence, outperforms state-of-the-art methods at inferring missing 3D data, and additionally provides covariance estimates of the uncertainty.

Bundle adjustment jointly optimizes camera intrinsics and extrinsics and 3D point triangulation to reconstruct a static scene. The triangulation constraint however is invalid for moving points captured in multiple unsynchronized videos and bundle adjustment is not purposed to estimate the temporal alignment between cameras. In this paper, we present a spatiotemporal bundle adjustment approach that jointly optimizes four coupled sub-problems: estimating camera intrinsics and extrinsics, triangulating 3D static points, as well as subframe temporal alignment between cameras and estimating 3D trajectories of dynamic points. Key to our joint optimization is the careful integration of physics-based motion priors within the reconstruction pipeline, validated on a large motion capture corpus. We present an end-to-end pipeline that takes multiple uncalibrated and unsynchronized video streams and produces a dynamic reconstruction of the event. Because the videos are aligned with sub-frame precision, we reconstruct 3D trajectories of unconstrained outdoor activities at much higher temporal resolution than the input videos.

Pose Machines provide a sequential prediction framework for learning rich implicit spatial models. In this work we show a systematic design for how convolutional networks can be incorporated into the pose machine framework for learning image features and image-dependent spatial models for the task of pose estimation. The contribution of this paper is to implicitly model long-range dependencies between variables in structured prediction tasks such as articulated pose estimation. We achieve this by designing a sequential architecture composed of convolutional networks that directly operate on belief maps from previous stages, producing increasingly refined estimates for part locations, without the need for explicit graphical model-style inference. Our approach addresses the characteristic difficulty of vanishing gradients during training by providing a natural learning objective function that enforces intermediate supervision, thereby replenishing back-propagated gradients and conditioning the learning procedure. We demonstrate state-of-the-art performance and outperform competing methods on standard benchmarks including the MPII, LSP, and FLIC datasets.

Real-time recognition of the 6DOF pose of textureless objects is a fundamental and challenging problem in robotics. We present a novel approach to perform real-time estimation of the viewpoint, scale, and translation of an object in RGB and RGB-D image captures. In this work, we use a 3D model to render example poses of a textureless object, and find the nearest match to the input image using a GPU implementation. To achieve invariance to illumination and appearance across an object, we transform images to the Laplacian of Gaussian space. To perform real-time matching, we introduce a novel reshaping of the template set and the image, and we restructure the traditional normalized cross-correlation operation to leverage the GPU for fast matrix-matrix multiplication. We provide further speed up of large-scale template matching by contributing a dimensionality reduction approach using principal component analysis, and a candidate elimination method. Our method achieves state-of-the-art performance as shown by qualitative results and quantitative comparisons to pre-existing methods.

Active illumination based methods have a trade-off between acquisition time and resolution of the estimated 3D shapes. Multi-shot approaches can generate dense reconstructions but require stationary scenes. Single-shot methods are applicable to dynamic objects but can only estimate sparse reconstructions and are sensitive to surface texture. We present a single-shot approach to produce dense shape reconstructions of highly textured objects illuminated by one or more projectors. The key to our approach is an image decomposition scheme that can recover the illumination image of different projectors and the texture images of the scene from their mixed appearances. We focus on three cases of mixed appearances: the illumination from one projector onto textured surface, illumination from multiple projectors onto a textureless surface, or their combined effect. Our method can accurately compute per-pixel warps from the illumination patterns and the texture template to the observed image. The texture template is obtained by interleaving the projection sequence with an all-white pattern. The estimated warps are reliable even with infrequent interleaved projection and strong object deformation. Thus, we obtain detailed shape reconstruction and dense motion tracking of the textured surfaces. The proposed method, implemented using a one camera and two projectors system, is validated on synthetic and real data containing subtle non-rigid surface deformations.

Photometric stereo (PS) is an established technique for high-detail reconstruction of 3D geometry and appearance. To correct for surface integration errors, PS is often combined with multiview stereo (MVS). With dynamic objects, PS reconstruction also faces the problem of computing optical flow (OF) for image alignment under rapid changes in illumination. Current PS methods typically compute optical flow and MVS as independent stages, each one with its own limitations and errors introduced by early regularization. In contrast, scene flow methods estimate geometry and motion, but lack the fine detail from PS. This paper proposes photogeometric scene flow (PGSF) for high-quality dynamic 3D reconstruction. PGSF performs PS, OF, and MVS simultaneously. It is based on two key observations: (i) while image alignment improves PS, PS allows for surfaces to be relit to improve alignment, (ii) PS provides surface gradients that render the smoothness term in MVS unnecessary, leading to truly data-driven, continuous depth estimates. This synergy is demonstrated in the quality of the resulting RGB appearance, 3D geometry, and 3D motion.

We present an approach to capture the 3D structure and motion of a group of people engaged in a social interaction. The core challenges in capturing social interactions are: (1) occlusion is functional and frequent, (2) subtle motion needs to be measured over a space large enough to host a social group, and (3) human appearance and configuration variation is immense. The Panoptic Studio is a system organized around the thesis that social interactions should be measured through the perceptual integration of a large variety of view points. We present a modularized system designed around this principle, consisting of integrated structural, hardware, and software innovations. The system takes, as input, 480 synchronized video streams of multiple people engaged in social activities, and produces, as output, the labeled time-varying 3D structure of anatomical landmarks on individuals in the space. The algorithmic contributions include a hierarchical approach for generating skeletal trajectory proposals, and an optimization framework for skeletal reconstruction with trajectory re-association.

Given the current profusion of devices for viewing media, video content created at one aspect ratio is often viewed on displays with different aspect ratios. Many previous solutions address this problem by retargeting or resizing the video, but a more general solution would re-edit the video for the new display. Our method employs the three primary editing operations: pan, cut, and zoom. We let viewers implicitly reveal what is important in a video by tracking their gaze as they watch the video. We present an algorithm that optimizes the path of a cropping window based on the collected eyetracking data, finds places to cut, and computes the size of the cropping window. We present results on a variety of video clips, including close-up and distant shots, and stationary and moving cameras. We conduct two experiments to evaluate our results. First, we eyetrack viewers on the result videos generated by our algorithm, and second, we perform a subjective assessment of viewer preference. These experiments show that viewer gaze patterns are similar on our result videos and on the original video clips, and that viewers prefer our results to an optimized crop-and-warp algorithm.

Many traditional challenges in reconstructing 3D motion, such as matching across wide baselines and handling occlusion, reduce in significance as the number of unique viewpoints increases. However, to obtain this benefit, a new challenge arises: estimating precisely which cameras observe which points at each instant in time. We present a maximum a posteriori (MAP) estimate of the time-varying visibility of the target points to reconstruct the 3D motion of an event from a large number of cameras. Our algorithm takes, as input, camera poses and image sequences, and outputs the time-varying set of the cameras in which a target patch is visible and its reconstructed trajectory. We model visibility estimation as a MAP estimate by incorporating various cues including photometric consistency, motion consistency, and geometric consistency, in conjunction with a prior that rewards consistent visibilities in proximal cameras. An optimal estimate of visibility is obtained by finding the minimum cut of a capacitated graph over cameras. We demonstrate that our method estimates visibility with greater accuracy, and increases tracking performance producing longer trajectories, at more locations, and at higher accuracies than methods that ignore visibility or use photometric consistency alone.

We present Marvin, a system that can search physical objects using a mobile or wearable device. It integrates HOG-based object recognition, SURF-based localization information, automatic speech recognition, and user feedback information with a probabilistic model to recognize the “object of interest” at high accuracy and at interactive speeds. Once the object of interest is recognized, the information that the user is querying, e.g. reviews, options, etc., is displayed on the user's mobile or wearable device. We tested this prototype in a real-world retail store during business hours, with varied degree of background noise and clutter. We show that this multi-modal approach achieves superior recognition accuracy compared to using a vision system alone, especially in cluttered scenes where a vision system would be unable to distinguish which object is of interest to the user without additional input. It is computationally able to scale to large numbers of objects by focusing compute-intensive resources on the objects most likely to be of interest, inferred from user speech and implicit localization information. We present the system architecture, the probabilistic model that integrates the multi-modal information, and empirical results showing the benefits of multi-modal integration.

We present an approach that takes multiple videos captured by social cameras---cameras that are carried or worn by members of the group involved in an activity---and produces a coherent "cut" video of the activity. Footage from social cameras contains an intimate, personalized view that reflects the part of an event that was of importance to the camera operator (or wearer). We leverage the insight that social cameras share the focus of attention of the people carrying them. We use this insight to determine where the important "content" in a scene is taking place, and use it in conjunction with cinematographic guidelines to select which cameras to cut to and to determine the timing of those cuts. A trellis graph representation is used to optimize an objective function that maximizes coverage of the important content in the scene, while respecting cinematographic guidelines such as the 180-degree rule and avoiding jump cuts. We demonstrate cuts of the videos in various styles and lengths for a number of scenarios, including sports games, street performances, family activities, and social get-togethers. We evaluate our results through an in-depth analysis of the cuts in the resulting videos and through comparison with videos produced by a professional editor and existing commercial solutions.

Photo-editing software restricts the control of objects in a photograph to the 2D image plane. We present a method that enables users to perform the full range of 3D manipulations, including scaling, rotation, translation, and nonrigid deformations, to an object in a photograph. As 3D manipulations often reveal parts of the object that are hidden in the original photograph, our approach uses publicly available 3D models to guide the completion of the geometry and appearance of the revealed areas of the object. The completion process leverages the structure and symmetry in the stock 3D model to factor out the effects of illumination, and to complete the appearance of the object. We demonstrate our system by producing object manipulations that would be impossible in traditional 2D photo-editing programs, such as turning a car over, making a paper-crane flap its wings, or manipulating airplanes in a historical photograph to change its story.

In this paper, we describe a method to represent and discover adversarial group behavior in a continuous domain. In comparison to other types of behavior, adversarial behavior is heavily structured as the location of a player (or agent) is dependent both on their teammates and adversaries, in addition to the tactics or strategies of the team. We present a method which can exploit this relationship through the use of a spatiotemporal basis model. As players constantly change roles during a match, we show that employing a "role-based" representation instead of one based on player "identity" can best exploit the playing structure. As vision-based systems currently do not provide perfect detection/tracking (e.g. missed or false detections), we show that our compact representation can effectively "denoise" erroneous detections as well as enabling temporal analysis, which was previously prohibitive due to the dimensionality of the signal. To evaluate our approach, we used a fully instrumented field-hockey pitch with 8 fixed high-definition (HD) cameras and evaluated our approach on approximately 200,000 frames of data from a state-of-the-art real-time player detector and compare it to manually labelled data.

The human body is structurally symmetric. Tracking by detection approaches for human pose suffer from double counting, where the same image evidence is used to explain two separate but symmetric parts, such as the left and right feet. Double counting, if left unaddressed can critically affect subsequent processes, such as action recognition, affordance estimation, and pose reconstruction. In this work, we present an occlusion aware algorithm for tracking human pose in an image sequence, that addresses the problem of double counting. Our key insight is that tracking human pose can be cast as a multi-target tracking problem where the ”targets” are related by an underlying articulated structure. The human body is modeled as a combination of singleton parts (such as the head and neck) and symmetric pairs of parts (such as the shoulders, knees, and feet). Symmetric body parts are jointly tracked with mutual exclusion constraints to prevent double counting by reasoning about occlusion. We evaluate our algorithm on an outdoor dataset with natural background clutter, a standard indoor dataset (HumanEva-I), and compare against a state of the art pose estimation algorithm.

We present a method to predict primary gaze behavior in a social scene. Inspired by the study of electric fields, we posit "social charges"-latent quantities that drive the primary gaze behavior of members of a social group. These charges induce a gradient field that defines the relationship between the social charges and the primary gaze direction of members in the scene. This field model is used to predict primary gaze behavior at any location or time in the scene. We present an algorithm to estimate the time-varying behavior of these charges from the primary gaze behavior of measured observers in the scene. We validate the model by evaluating its predictive precision via cross-validation in a variety of social scenes.

Generating live broadcasts of sporting events requires a coordinated crew of camera operators, directors, and technical personnel to control and switch between multiple cameras to tell the evolving story of a game. In this paper, we present an unimodal interface concept that allows one person to cover live sporting action by controlling multiple cameras and and determining which view to broadcast. The interface exploits the structure of sports broadcasts which typically switch between a zoomed out game-camera view (which records the strategic team-level play), and a zoomed in iso-camera view (which captures the animated adversarial relations between opposing players). The operator simultaneously controls multiple pan-tilt-zoom cameras by pointing at a location on the touch screen, and selects which camera to broadcast using one or two points of contact. The image from the selected camera is superimposed on top of a wide-angle view captured from a context-camera which provides the operator with periphery information (which is useful for ensuring good framing while controlling the camera). We show that by unifying directorial and camera operation functions, we can achieve comparable broadcast quality to a multi-person crew, while reducing cost, logistical, and communication complexities.

Comics are a compelling, though complex, visual storytelling medium. Researchers are interested in the process of comic art creation to be able to automatically tell new stories, and also, summarize videos and catalog large collections of photographs for example. A primary organizing principle used by artists to lay out the components of comic art (panels, word bubbles, objects inside each panel) is to lead the viewer's attention along a deliberate visual route that reveals the narrative. If artists are successful in leading viewer attention, then their intended visual route would be accessible through recorded viewer attention, i.e., eyetracking data. In this paper, we conduct an experiment to verify if artists are successful in their goal of leading viewer gaze. We eyetrack viewers on images taken from comic books, as well as photographs taken by experts, amateur photographers and a robot. Our data analyses show that there is increased consistency in viewer gaze for comic pictures versus photographs taken by a robot and by amateur photographers, thus confirming that comic artists do indeed direct the flow of viewer attention.

Point-based targets, such as checkerboards, are often not practical for outdoor camera calibration, as cameras are usually at significant heights requiring extremely large calibration patterns on the ground. Fortunately, it is possible to make use of existing non-point landmarks in the scene by formulating camera calibration in terms of image alignment. In this paper, we simultaneously estimate the camera intrinsic, extrinsic and lens distortion parameters directly by aligning to a planar schematic of the scene. For cameras with square pixels and known principal point, finding the parameters to such an image warp is equivalent to calibrating the camera. Overhead schematics of many environments resemble edge images. Edge images are difficult to align using image-based algorithms because both the image and its gradient are sparse. We employ a `long range' gradient which enables informative parameter updates at each iteration while maintaining a precise alignment measure. As a result, we are able to calibrate our camera models robustly using regular gradient-based image alignment, given an initial ground to image homography estimate.

A variety of dynamic objects, such as faces, bodies, and cloth, are represented in computer graphics as a collection of moving spatial landmarks. Spatiotemporal data is inherent in a number of graphics applications including animation, simulation, and object and camera tracking. The principal modes of variation in the spatial geometry of objects are typically modeled using dimensionality reduction techniques, while concurrently, trajectory representations like splines and autoregressive models are widely used to exploit the temporal regularity of deformation. In this article, we present the bilinear spatiotemporal basis as a model that simultaneously exploits spatial and temporal regularity while maintaining the ability to generalize well to new sequences. This factorization allows the use of analytical, predefined functions to represent temporal variation (e.g., B-Splines or the Discrete Cosine Transform) resulting in efficient model representation and estimation. The model can be interpreted as representing the data as a linear combination of spatiotemporal sequences consisting of shape modes oscillating over time at key frequencies. We apply the bilinear model to natural spatiotemporal phenomena, including face, body, and cloth motion data, and compare it in terms of compaction, generalization ability, predictive precision, and efficiency to existing models. We demonstrate the application of the model to a number of graphics tasks including labeling, gap-filling, denoising, and motion touch-up.

Drawing shapes by hand and manipulating computer-generated objects are the two dominant forms of animation. Though each medium has its own advantages, the techniques developed for one medium are not easily leveraged in the other medium because hand animation is two-dimensional, and inferring the third dimension is mathematically ambiguous. A second challenge is that the character is a consistent three-dimensional (3D) object in computer animation while hand animators introduce geometric inconsistencies in the two-dimensional (2D) shapes to better convey a character's emotional state and personality. In this work, we identify 3D proxies to connect hand-drawn animation and 3D computer animation. We present an integrated approach to generate three levels of 3D proxies: single-points, polygonal shapes, and a full joint hierarchy. We demonstrate how this approach enables one medium to take advantage of techniques developed for the other; for example, 3D physical simulation is used to create clothes for a hand-animated character, and a traditionally trained animator is able to influence the performance of a 3D character while drawing with paper and pencil.

In theory, the precision of structure from motion estimation is known to increase as camera motion increases. In practice, larger camera motions induce motion blur, particularly in low light where longer exposures are needed. If the camera center moves during exposure, the trajectory traces in a motion-blurred image encode the underlying 3D structure of points and the motion of the camera. In this paper, we propose an algorithm to explicitly estimate the 3D structure of point light sources and camera motion from a motion-blurred image in a low light scene with point light sources. The algorithm identifies extremal points of the traces mapped out by the point sources in the image and classifies them into start and end sets. Each trace is charted out incrementally using local curvature, providing correspondences between start and end points. We use these correspondences to obtain an initial estimate of the epipolar geometry embedded in a motion-blurred image. The reconstruction and the 2D traces are used to estimate the motion of the camera during the interval of capture, and multiple view bundle adjustment is applied to refine the estimates.

An articulated trajectory is defined as a trajectory that remains at a fixed distance with respect to a parent trajectory. In this paper, we present a method to reconstruct an articulated trajectory in three dimensions given the two dimensional projection of the articulated trajectory, the 3D parent trajectory, and the camera pose at each time instant. This is a core challenge in reconstructing the 3D motion of articulated structures such as the human body because endpoints of each limb form articulated trajectories. We simultaneously apply activity-independent spatial and temporal constraints, in the form of fixed 3D distance to the parent trajectory and smooth 3D motion. There exist two solutions that satisfy each instantaneous 2D projection and articulation constraint (a ray intersects a sphere at up to two locations) and we show that resolving this ambiguity by enforcing smoothness is equivalent to solving a binary quadratic programming problem. A geometric analysis of the reconstruction of articulated trajectories is also presented and a measure of the reconstructibility of an articulated trajectory is proposed.

Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes. These bases are object dependent and therefore have to be estimated anew for each video sequence. In contrast, we propose a dual approach to describe the evolving 3D structure in trajectory space by a linear combination of basis trajectories. We describe the dual relationship between the two approaches, showing that they both have equal power for representing 3D structure. We further show that the temporal smoothness in 3D trajectories alone can be used for recovering nonrigid structure from a moving camera. The principal advantage of expressing deforming 3D structure in trajectory space is that we can define an object independent basis. This results in a significant reduction in unknowns and corresponding stability in estimation. We propose the use of the Discrete Cosine Transform (DCT) as the object independent basis and empirically demonstrate that it approaches Principal Component Analysis (PCA) for natural motions. We report the performance of the proposed method, quantitatively using motion capture data, and qualitatively on several video sequences exhibiting nonrigid motions, including piecewise rigid motion, partially nonrigid motion (such as a facial expressions), and highly nonrigid motion (such as a person walking or dancing).

In this paper, we describe the explicit application of articulation constraints for estimating the motion of a system of articulated planes. We relate articulations to the relative homography between planes and show that these articulations translate into linearized equality constraints on a linear least-squares system, which can be solved efficiently using a Karush-Kuhn-Tucker system. The articulation constraints can be applied for both gradient-based and feature-based motion estimation algorithms and to illustrate this, we describe a gradient-based motion estimation algorithm for an affine camera and a feature-based motion estimation algorithm for a projective camera that explicitly enforces articulation constraints. We show that explicit application of articulation constraints leads to numerically stable estimates of motion. The simultaneous computation of motion estimates for all of the articulated planes in a scene allows us to handle scene areas where there is limited texture information and areas that leave the field of view. Our results demonstrate the wide applicability of the algorithm in a variety of challenging real-world cases such as human body tracking, motion estimation of rigid, piecewise planar scenes, and motion estimation of triangulated meshes.

Motion capture technology generally requires that recordings be performed in a laboratory or closed stage setting with controlled lighting. This restriction precludes the capture of motions that require an outdoor setting or the traversal of large areas. In this paper, we present the theory and practice of using body-mounted cameras to reconstruct the motion of a subject. Outward-looking cameras are attached to the limbs of the subject, and the joint angles and root pose are estimated through non-linear optimization. The optimization objective function incorporates terms for image matching error and temporal continuity of motion. Structure-from-motion is used to estimate the skeleton structure and to provide initialization for the non-linear optimization procedure. Global motion is estimated and drift is controlled by matching the captured set of videos to reference imagery. We show results in settings where capture would be difficult or impossible with traditional motion capture systems, including walking outside and swinging on monkey bars. The quality of the motion reconstruction is evaluated by comparing our results against motion capture data produced by a commercially available optical system.

In factorization approaches to nonrigid structure from motion, the 3D shape of a deforming object is usually modeled as a linear combination of a small number of basis shapes. The original approach to simultaneously estimate the shape basis and nonrigid structure exploited ortho-normality constraints for metric rectification. Recently, it has been asserted that structure recovery through ortho-normality constraints alone is inherently ambiguous and cannot result in a unique solution. This assertion has been accepted as conventional wisdom and is the justification of many remedial heuristics in literature. Our key contribution is to prove that ortho-normality constraints are in fact sufficient to recover the 3D structure from image observations alone. We characterize the true nature of the ambiguity in using ortho-normality constraints for the shape basis and show that it has no impact on structure reconstruction. We conclude from our experimentation that the primary challenge in using shape basis for nonrigid structure from motion is the difficulty in the optimization problem rather than the ambiguity in ortho-normality constraints.

Background subtraction algorithms define the background as parts of a scene that are at rest. Traditionally, these algorithms assume a stationary camera, and identify moving objects by detecting areas in a video that change over time. In this paper, we extend the concept of `subtracting' areas at rest to apply to video captured from a freely moving camera. We do not assume that the background is well-approximated by a plane or that the camera center remains stationary during motion. The method operates entirely using 2D image measurements without requiring an explicit 3D reconstruction of the scene. A sparse model of background is built by robustly estimating a compact trajectory basis from trajectories of salient features across the video, and the background is `subtracted' by removing trajectories that lie within the space spanned by the basis. Foreground and background appearance models are then built, and an optimal pixel-wise foreground/background labeling is obtained by efficiently maximizing a posterior function.

This paper presents a method to create an illusion of seeing moving objects through occluding surfaces in a video. This illusion is achieved by transferring information from a camera viewing the occluded area. In typical view interpolation approaches for 3D scenes, some form of correspondence across views is required. For occluded areas, establishing direct correspondence is impossible as information is missing in one of the views. Instead, we use a 2D projective invariant to capture information about occluded objects (which may be moving). Since invariants are quantities that do not change across views, a visually compelling rendering of hidden areas is achieved without the need for explicit correspondences. A piece-wise planar model of the scene allows the entire rendering process to take place without any 3D reconstruction, while still producing visual parallax. Because of the simplicity and robustness of the 2D invariant, we are able to transfer both static backgrounds and moving objects in real time. A complete working system has been implemented that runs live at 5Hz. Applications for this technology include the ability to look through corners at tight intersections for automobile safety, concurrent visualization of a surveillance camera network, and monitoring systems for patients/elderly/children.

In this paper, we describe the explicit application of articulation constraints for estimating the motion of a system of planes. We relate articulations to the relative homography between planes and show that for affine cameras, these articulations translate into linear equality constraints on a linear least squares system, yielding accurate and numerically stable estimates of motion. The global nature of motion estimation allows us to handle areas where there is limited texture information and areas that leave the field of view. Our results demonstrate the accuracy of the algorithm in a variety of cases such as human body tracking, motion estimation of rigid, piecewise planar scenes and motion estimation of triangulated meshes.

In this paper, we propose an algorithm for sustained tracking of humans, where we combine frame-to-frame articulated motion estimation with a per-frame body detection algorithm. The proposed approach can automatically recover from tracking error and drift. The frame-to-frame motion estimation algorithm replaces traditional dynamic models within a filtering framework. Stable and accurate per-frame motion is estimated via an image-gradient based algorithm that solves a linear constrained least squares system. The per-frame detector learns appearance of different body parts and dasiasketchespsila expected gradient maps to detect discriminant pose configurations in images. The resulting online algorithm is computationally efficient and has been widely tested on a large dataset of sequences of drivers in vehicles. It shows stability and sustained accuracy over thousands of frames.

Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes, which have to be estimated anew for each video sequence. In contrast, we propose that the evolving 3D structure be described by a linear combination of basis trajectories. The principal advantage of this lateral approach is that we do not need to estimate any basis vectors during computation. Instead, we show that generic bases over trajectories, such as the Discrete Cosine Transform (DCT) bases, can be used to effectively describe most real motions. This results in a significant reduction in unknowns, and corresponding stability, in estimation. We report empirical performance, quantitatively using motion capture data and qualitatively on several video sequences exhibiting nonrigid motions including piece-wise rigid motion, articulated motion, partially nonrigid motion (such as a facial expression), and highly nonrigid motion (such as a person dancing).

A camera mounted on an aerial vehicle provides an excellent means for monitoring large areas of a scene. Utilizing several such cameras on different aerial vehicles allows further flexibility, in terms of increased visual scope and in the pursuit of multiple targets. In this paper, we address the problem of associating objects across multiple airborne cameras. Since the cameras are moving and often widely separated, direct appearance-based or proximity-based constraints cannot be used. Instead, we exploit geometric constraints on the relationship between the motion of each object across cameras, to test multiple association hypotheses, without assuming any prior calibration information. Given our scene model, we propose a likelihood function for evaluating a hypothesized association between observations in multiple cameras that is geometrically motivated. Since multiple cameras exist, ensuring coherency in association is an essential requirement, e.g. that transitive closure is maintained between more than two cameras. To ensure such coherency we pose the problem of maximizing the likelihood function as a k-dimensional matching and use an approximation to find the optimal assignment of association. Using the proposed error function, canonical trajectories of each object and optimal estimates of inter-camera transformations (in a maximum likelihood sense) are computed. Finally, we show that as a result of associating objects across the cameras, a concurrent visualization of multiple aerial video streams is possible and that, under special conditions, trajectories interrupted due to occlusion or missing detections can be repaired. Results are shown on a number of real and controlled scenarios with multiple objects observed by multiple cameras, validating our qualitative models, and through simulation quantitative performance is also reported.

In this paper, a projection model is presented for cameras moving at constant velocity (which we refer to as Galilean cameras). To that end, we introduce the concept of spacetime projection and show that perspective imaging and linear pushbroom imaging are specializations of the proposed model. The epipolar geometry between two such cameras is developed and we derive the Galilean fundamental matrix. We show how six different "fundamental" matrices can be directly recovered from the Galilean fundamental matrix including the classic fundamental matrix, the linear pushbroom (LP) fundamental matrix and a fundamental matrix relating epipolar plane images (EPIs). To estimate the parameters of this fundamental matrix and the mapping between videos in the case of planar scenes we describe linear algorithms and report experimental performance of these algorithms.

The fundamental matrix is a central construct in the analysis of images captured from a pair of cameras and many feature-based methods have been proposed for its computation. In this paper, we propose a direct method for estimating the fundamental matrix where the motion between the frames is small (e.g. between successive frames of a video). To achieve this, a warping function is presented for the fundamental matrix by using the brightness constancy constraint in conjunction with geometric constraints. Using this warping function, an iterative hierarchical algorithm is described to recover accurate estimates of the fundamental matrix. We present results of experimentation to evaluate the performance of the proposed approach and demonstrate improved accuracy in the computation of the fundamental matrix.

The ability to associate objects across multiple views allows co-operative use of an ensemble cameras for scene understanding. In this paper, we present a principled solution to object association where both the scene and the object motion are modeled. By making the motion model of each object with respect to time explicit, we are able to solve the trajectory association problem in a unified framework for overlapping or non-overlapping cameras. We recover the assignment of associations while simultaneously computing the maximum likelihood estimates of the inter-camera homographies and the trajectory parameters using the expectation maximization algorithm. Quantitative results on simulations are reported along with several results on real data.

We present a nonparametric mode-seeking algorithm, called medoidshift, based on approximating the local gradient using a weighted estimate of medoids. Like meanshift, medoidshift clustering automatically computes the number of clusters and the data does not have to be linearly separable. Unlike meanshift, the proposed algorithm does not require the definition of a mean. This property allows medoidshift to find modes even when only a distance measure between samples is defined. In this sense, the relationship between the medoidshift algorithm and the meanshift algorithm is similar to the relationship between the k-medoids and the k-means algorithms. We show that medoidshifts can also be used for incremental clustering of growing datasets by recycling previous computations. We present experimental results using medoidshift for image segmentation, incremental clustering for shot segmentation and clustering on nonlinearly separable data.

We propose a method for recovering the affine geometry of a dynamically textured plane from a video sequence taken by an uncalibrated, fixed, perspective camera. Some instances of approximately planar surfaces that are coated with a dynamic texture include large water bodies, (such as lakes and oceans), heavy traffic, dense crowds, escalators, and foliage in the wind. Under the assumption of translational dynamic textures, we propose a direct algorithm for the estimation of the inter-frame elation that does not require explicit identification of texels or movetons. In addition, we develop a general algorithm for recovering the affine geometry of homogeneous dynamic textures by identifying a constraint on the expected values of motion magnitudes. We report experimental results on several real videos of dynamic texture found in the world.

This paper presents a novel approach to object recognition involving a sparse 2D model and matching using video. The model is generated on the basis of geometry and image measurables only. We first identify the underlying topological structure of an image dataset containing different views of the objects and represent it as a neighborhood graph. The graph is then refined by identifying redundant images and removing them using morphing. This gives a smaller dataset leading to reduced space requirements and faster matching. Finally we exploit motion continuity in video and extend our algorithm to perform matching based on video input and demonstrate that the results obtained using a video sequence are much robust than using a single image. Our approach is novel in that we do not require any knowledge of camera calibration or viewpoint while generating the model. We also do not assume any constraint on motion of object in test video other than following a smooth trajectory.

Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovations are presented over existing approaches. Firstly, the model of the intensities of image pixels as independently distributed random variables is challenged and it is asserted that useful correlation exists in the intensities of spatially proximal pixels. This correlation is exploited to sustain high levels of detection accuracy in the presence of nominal camera motion and dynamic textures. By using a non-parametric density estimation method over a joint domain-range representation of image pixels, multi-modal spatial uncertainties and complex dependencies between the domain (location) and range (color) are directly modeled. Secondly, temporal persistence is proposed as a detection criteria. Unlike previous approaches to object detection which detect objects by building adaptive models of the only background, the foreground is also modeled to augment the detection of objects (without explicit tracking) since objects detected in a preceding frame contain substantial evidence for detection in a current frame. Third, the background and foreground models are used competitively in a MAP-MRF decision framework, stressing spatial context as a condition of pixel-wise labeling and the posterior function is maximized efficiently using graph cuts. Experimental validation of the proposed method is presented on a diverse set of dynamic scenes.

A camera mounted on an aerial vehicle provides an excellent means for monitoring large areas of a scene. Utilizing several such cameras on different aerial vehicles allows further flexibility, in terms of increased visual scope and in the pursuit of multiple targets. In this paper, we address the problem of tracking objects across multiple moving airborne cameras. Since the cameras are moving and often widely separated, direct appearance-based or proximity-based constraints cannot be used. Instead, we exploit geometric constraints on the relationship between the motions of each object across cameras, to test multiple correspondence hypotheses, without assuming any prior calibration information. We propose a statistically and geometrically meaningful means of evaluating a hypothesized correspondence between two observations in different cameras. Second, since multiple cameras exist, ensuring coherency in correspondence, i.e. transitive closure is maintained between more than two cameras, is an essential requirement. To ensure such coherency we pose the problem of object tracking across cameras as a k-dimensional matching and use an approximation to find the maximum likelihood assignment of correspondence. Third, we show that as a result of tracking objects across the cameras, a concurrent visualization of multiple aerial video streams is possible. Results are shown on a number of real and controlled scenarios with multiple objects observed by multiple cameras, validating our qualitative models.

One of the fundamental challenges of recognizing actions is accounting for the variability that arises when arbitrary cameras capture humans performing actions. In this paper, we explicitly identify three important sources of variability: (1) viewpoint, (2) execution rate, and (3) anthropometry of actors, and propose a model of human actions that allows us to investigate all three. Our hypothesis is that the variability associated with the execution of an action can be closely approximated by a linear combination of action bases in joint spatio-temporal space. We demonstrate that such a model bounds the rank of a matrix of image measurements and that this bound can be used to achieve recognition of actions based only on imaged data. A test employing principal angles between subspaces that is robust to statistical fluctuations in measurement data is presented to find the membership of an instance of an action. The algorithm is applied to recognize several actions, and promising results have been obtained.

Accurate detection of moving objects is an important precursor to stable tracking or recognition. In this paper, we present an object detection scheme that has three innovations over existing approaches. First, the model of the intensities of image pixels as independent random variables is challenged and it is asserted that useful correlation exists in intensities of spatially proximal pixels. This correlation is exploited to sustain high levels of detection accuracy in the presence of dynamic backgrounds. By using a nonparametric density estimation method over a joint domain-range representation of image pixels, multimodal spatial uncertainties and complex dependencies between the domain (location) and range (color) are directly modeled. We propose a model of the background as a single probability density. Second, temporal persistence is proposed as a detection criterion. Unlike previous approaches to object detection which detect objects by building adaptive models of the background, the foreground is modeled to augment the detection of objects (without explicit tracking) since objects detected in the preceding frame contain substantial evidence for detection in the current frame. Finally, the background and foreground models are used competitively in a MAP-MRF decision framework, stressing spatial context as a condition of detecting interesting objects and the posterior function is maximized efficiently by finding the minimum cut of a capacitated graph. Experimental validation of the proposed method is performed and presented on a diverse set of dynamic scenes.