Search

Traditional methods for constructing high-quality, personalized head avatars from monocular videos demand extensive face captures and training time, posing a significant challenge for scalability. This paper introduces a novel approach to create high quality head avatar utilizing only a single or a few images per user. We learn a generative model for 3D animatable photo-realistic head avatar from a multi-view dataset of expressions from 2407 subjects, and leverage it as a prior for creating personalized avatar from few-shot images. Different from previous 3D-aware face generative models, our prior is built with a 3DMM-anchored neural radiance field backbone, which we show to be more effective for avatar creation through auto-decoding based on few-shot inputs. We also handle unstable 3DMM fitting by jointly optimizing the 3DMM fitting and camera calibration that leads to better few-shot adaptation. Our method demonstrates compelling results and outperforms existing state-of-the-art methods for few-shot avatar adaptation, paving the way for more efficient and personalized avatar creation.

This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of five primary body signals including gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cameras are used to capture 772 distinctive subjects across gender, ethnicity, age, and style. With the multiview image streams, we reconstruct high fidelity body expressions using 3D mesh models, which allows representing view-specific appearance. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complementary to the existing datasets of human body expressions with limited views and subjects such as MPII-Gaze, Multi-PIE, Human3.6M, and Panoptic Studio datasets. Based on HUMBI, we formulate a new benchmark challenge of a pose-guided appearance rendering task that aims to substantially extend photorealism in modeling diverse human expressions in 3D, which is the key enabling factor of authentic social tele-presence. HUMBI is publicly available at http://humbi-data.net, Comment: 18 pages; Accepted to TPAMI

This paper presents a new end-to-end semi-supervised framework to learn a dense keypoint detector using unlabeled multiview images. A key challenge lies in finding the exact correspondences between the dense keypoints in multiple views since the inverse of the keypoint mapping can be neither analytically derived nor differentiated. This limits applying existing multiview supervision approaches used to learn sparse keypoints that rely on the exact correspondences. To address this challenge, we derive a new probabilistic epipolar constraint that encodes the two desired properties. (1) Soft correspondence: we define a matchability, which measures a likelihood of a point matching to the other image's corresponding point, thus relaxing the requirement of the exact correspondences. (2) Geometric consistency: every point in the continuous correspondence fields must satisfy the multiview consistency collectively. We formulate a probabilistic epipolar constraint using a weighted average of epipolar errors through the matchability thereby generalizing the point-to-point geometric error to the field-to-field geometric error. This generalization facilitates learning a geometrically coherent dense keypoint detection model by utilizing a large number of unlabeled multiview images. Additionally, to prevent degenerative cases, we employ a distillation-based regularization by using a pretrained model. Finally, we design a new neural network architecture, made of twin networks, that effectively minimizes the probabilistic epipolar errors of all possible correspondences between two view images by building affinity matrices. Our method shows superior performance compared to existing methods, including non-differentiable bootstrapping in terms of keypoint accuracy, multiview consistency, and 3D reconstruction accuracy., Comment: Published as a conference paper at NeurIPS 2021

This paper presents a new large multiview dataset called HUMBI for human body expressions with natural clothing. The goal of HUMBI is to facilitate modeling view-specific appearance and geometry of gaze, face, hand, body, and garment from assorted people. 107 synchronized HD cameras are used to capture 772 distinctive subjects across gender, ethnicity, age, and physical condition. With the multiview image streams, we reconstruct high fidelity body expressions using 3D mesh models, which allows representing view-specific appearance using their canonical atlas. We demonstrate that HUMBI is highly effective in learning and reconstructing a complete human model and is complementary to the existing datasets of human body expressions with limited views and subjects such as MPII-Gaze, Multi-PIE, Human3.6M, and Panoptic Studio datasets.

We report overall design considerations and preliminary results for a new haptic rendering device based on an audio loudspeaker. Our application models tissue properties during microsurgery. For example, the device could respond to the tip of a tool by simulating a particular tissue, displaying a desired compressibility and viscosity, giving way as the tissue is disrupted, or exhibiting independent motion, such as that caused by pulsations in blood pressure. Although limited to one degree of freedom and with a relatively small range of displacement compared to other available haptic rendering devices, our design exhibits high bandwidth, low friction, low hysteresis, and low mass. These features are consistent with modeling interactions with delicate tissues during microsurgery. In addition, our haptic rendering device is designed to be simple and inexpensive to manufacture, in part through an innovative method of measuring displacement by existing variations in the speaker’s inductance as the voice coil moves over the permanent magnet. Low latency and jitter are achieved by running the real-time simulation models on a dedicated microprocessor, while maintaining bidirectional communication with a standard laptop computer for user controls and data logging.

We report overall design considerations and preliminary results for a new haptic rendering device based on an audio loudspeaker. Our application models tissue properties during microsurgery. For example, the device could respond to the tip of a tool by simulating a particular tissue, displaying a desired compressibility and viscosity, giving way as the tissue is disrupted, or exhibiting independent motion, such as that caused by pulsations in blood pressure. Although limited to one degree of freedom and with a relatively small range of displacement compared to other available haptic rendering devices, our design exhibits high bandwidth, low friction, low hysteresis, and low mass. These features are consistent with modeling interactions with delicate tissues during microsurgery. In addition, our haptic rendering device is designed to be simple and inexpensive to manufacture, in part through an innovative method of measuring displacement by existing variations in the speaker’s inductance as the voice coil moves over the permanent magnet. Low latency and jitter are achieved by running the real-time simulation models on a dedicated microprocessor, while maintaining bidirectional communication with a standard laptop computer for user controls and data logging.