This paper proposes Virtual Fitting Room (VFR), a novel video generative model that produces arbitrarily long virtual try-on videos. Our VFR models long video generation tasks as an auto-regressive, segment-by-segment generation process, eliminating the need for resource-intensive generation and lengthy video data, while providing the flexibility to generate videos of arbitrary length. The key challenges of this task are twofold: ensuring local smoothness between adjacent segments and maintaining global temporal consistency across different segments. To address these challenges, we propose our VFR framework, which ensures smoothness through a prefix video condition and enforces consistency with the anchor video — a 360°-view video that comprehensively captures the human's whole-body appearance. Our VFR generates minute-scale virtual try-on videos with both local smoothness and global temporal consistency under various motions, making it a pioneering work in long virtual try-on video generation. Project Page: https://immortalco.github.io/VirtualFittingRoom/.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception.

We present EgoHumans, a new multi-view multi-human video benchmark to advance the state-of-the-art of egocentric human 3D pose estimation and tracking. Existing ego-centric benchmarks either capture single subject or indoor-only scenarios, which limit the generalization of computer vision algorithms for real-world applications. We propose a novel 3D capture setup to construct a comprehensive ego-centric multi-human benchmark in the wild with annotations to support diverse tasks such as human detection, tracking, 2D/3D pose estimation, and mesh recovery. We leverage consumer-grade wearable camera-equipped glasses for the egocentric view, which enables us to capture dynamic activities like playing tennis, fencing, volleyball, etc. Furthermore, our multi-view setup generates accurate 3D ground truth even under severe or complete occlusion. The dataset consists of more than 125k egocentric images, spanning diverse scenes with a particular focus on challenging and unchoreographed multi-human activities and fast-moving egocentric views. We rigorously evaluate existing state-of-the-art methods and highlight their limitations in the egocentric scenario, specifically on multi-human tracking. To address such limitations, we propose EgoFormer, a novel approach with a multi-stream transformer architecture and explicit 3D spatial reasoning to estimate and track the human pose. EgoFormer significantly outperforms prior art by 13.6% IDF1 on the EgoHumans dataset.

Multi-person pose understanding from RGB videos involves three complex tasks: pose estimation, tracking and motion forecasting. Intuitively, accurate multi-person pose estimation facilitates robust tracking, and robust tracking builds crucial history for correct motion forecasting. Most existing works either focus on a single task or employ multi-stage approaches to solving multiple tasks separately, which tends to make sub-optimal decision at each stage and also fail to exploit correlations among the three tasks. In this paper, we propose Snipper, a unified framework to perform multi-person 3D pose estimation, tracking, and motion forecasting simultaneously in a single stage. We propose an efficient yet powerful deformable attention mechanism to aggregate spatiotemporal information from the video snippet. Building upon this deformable attention, a video transformer is learned to encode the spatiotemporal features from the multi-frame snippet and to decode informative pose features for multi-person pose queries. Finally, these pose queries are regressed to predict multi-person pose trajectories and future motions in a single shot. In the experiments, we show the effectiveness of Snipper on three challenging public datasets where our generic model rivals specialized state-of-art baselines for pose estimation, tracking, and forecasting. Code is available athttps://github.com/JimmyZou/Snipper.

This paper proposes a do-it-all neural model of human hands, named LISA. The model can capture accurate hand shape and appearance, generalize to arbitrary hand sub-jects, provide dense surface correspondences, be reconstructed from images in the wild, and can be easily an-imated. We train LISA by minimizing the shape and appearance losses on a large set of multi-view RGB image se-quences annotated with coarse 3D poses of the hand skele-ton. For a 3D point in the local hand coordinates, our model predicts the color and the signed distance with respect to each hand bone independently, and then combines the per-bone predictions using the predicted skinning weights. The shape, color, and pose representations are disentangled by design, enabling fine control of the selected hand param-eters. We experimentally demonstrate that LISA can ac-curately reconstruct a dynamic hand from monocular or multi-view sequences, achieving a noticeably higher qual-ity of reconstructed hand shapes compared to baseline approaches. Project page: https://www.iri.upc.edu/people/ecorona/lisa/.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of dailylife activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

Prior work for articulated 3D shape reconstruction often relies on specialized multi-view and depth sensors or pre-built deformable 3D models. Such methods do not scale to diverse sets of objects in the wild. We present a method that requires neither of them. It aims to create high-fidelity, articulated 3D models from many casual RGB videos in a differentiable rendering framework. Our key in-sight is to merge three schools of thought: (1) classic deformable shape models that make use of articulated bones and blend skinning, (2) canonical embeddings that establish correspondences between pixels and a canonical 3D model, and (3) volumetric neural radiance fields (NeRFs) that are amenable to gradient-based optimization. We introduce neural blend skinning models that allow for differentiable and invertible articulated deformations. When combined with canonical embeddings, such models allow us to establish dense correspondences across videos that can be self-supervised with cycle consistency. On real and synthetic datasets, our method shows higher-fidelity 3D reconstructions than prior works for humans and animals, with the ability to render realistic images from novel viewpoints. Project page: https://banmo-www.github.io/.

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.

Physical contact between hands and objects plays a critical role in human grasps. We show that optimizing the pose of a hand to achieve expected contact with an object can improve hand poses inferred via image-based methods. Given a hand mesh and an object mesh, a deep model trained on ground truth contact data infers desirable contact across the surfaces of the meshes. Then, ContactOpt efficiently optimizes the pose of the hand to achieve desirable contact using a differentiable contact model. Notably, our contact model encourages mesh interpenetration to approximate deformable soft tissue in the hand. In our evaluations, our methods result in grasps that better match ground truth contact, have lower kinematic error, and are significantly preferred by human participants. Code and models are available online1.

The combination of traditional rendering with neural networks in Deferred Neural Rendering (DNR) [38] provides a compelling balance between computational complexity and realism of the resulting images. Using skinned meshes for rendering articulating objects is a natural extension for the DNR framework and would open it up to a plethora of applications. However, in this case the neural shading step must account for deformations that are possibly not captured in the mesh, as well as alignment in-accuracies and dynamics—which can confound the DNR pipeline. We present Articulated Neural Rendering (ANR), a novel framework based on DNR which explicitly addresses its limitations for virtual human avatars. We show the superiority of ANR not only with respect to DNR but also with methods specialized for avatar creation and animation. In two user studies, we observe a clear preference for our avatar model and we demonstrate state-of-the-art performance on quantitative evaluation metrics. Perceptually, we observe better temporal stability, level of detail and plausibility. More results are available at our project page: https://anr-avatars.github.io.

Localizing objects and estimating their extent in 3D is an important step towards high-level 3D scene understanding, which has many applications in Augmented Reality and Robotics. We present ODAM, a system for 3D Object Detection, Association, and Mapping using posed RGB videos. The proposed system relies on a deep learning front-end to detect 3D objects from a given RGB frame and associate them to a global object-based map using a graph neural network (GNN). Based on these frame-to-model associations, our back-end optimizes object bounding volumes, represented as super-quadrics, under multi-view geometry constraints and the object scale prior. We validate the proposed system on ScanNet where we show a significant improvement over existing RGB-only methods.

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 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.

We present Occlusion-Net, a framework to predict 2D and 3D locations of occluded keypoints for objects, in a largely self-supervised manner. We use an off-the-shelf detector as input (like MaskRCNN) that is trained only on visible key point annotations. This is the only supervision used in this work. A graph encoder network then explicitly classifies invisible edges and a graph decoder network corrects the occluded keypoint locations from the initial detector. Central to this work is a trifocal tensor loss that provides indirect self-supervision for occluded keypoint locations that are visible in other views of the object. The 2D keypoints are then passed into a 3D graph network that estimates the 3D shape and camera pose using the self-supervised re-projection loss. At test time, our approach successfully localizes keypoints in a single view under a diverse set of severe occlusion settings. We demonstrate and evaluate our approach on synthetic CAD data as well as a large image set capturing vehicles at many busy city intersections. As an interesting aside, we compare the accuracy of human labels of invisible keypoints against those obtained from geometric trifocal-tensor loss.

Despite significant research in the area, reconstruction of multiple dynamic rigid objects (eg. vehicles) observed from wide-baseline, uncalibrated and unsynchronized cameras, remains hard. On one hand, feature tracking works well within each view but is hard to correspond across multiple cameras with limited overlap infields of view or due to occlusions. On the other hand, advances in deep learning have resulted in strong detectors that work across different viewpoints but are still not precise enough for triangulation-based reconstruction. In this work, we develop a framework to fuse both the single-view feature tracks and multiview detected part locations to significantly improve the detection, localization and reconstruction of moving vehicles, even in the presence of strong occlusions. We demonstrate our framework at a busy traffic intersection by reconstructing over 62 vehicles passing within a 3-minute window. We evaluate the different components within our framework and compare to alternate approaches such as reconstruction using tracking-by-detection.

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.

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.