Allen Y. Yang

Allen Y. Yang, Zihan Zhou, Arvind Ganesh et al.

L1-minimization refers to finding the minimum L1-norm solution to an underdetermined linear system b=Ax. Under certain conditions as described in compressive sensing theory, the minimum L1-norm solution is also the sparsest solution. In this paper, our study addresses the speed and scalability of its algorithms. In particular, we focus on the numerical implementation of a sparsity-based classification framework in robust face recognition, where sparse representation is sought to recover human identities from very high-dimensional facial images that may be corrupted by illumination, facial disguise, and pose variation. Although the underlying numerical problem is a linear program, traditional algorithms are known to suffer poor scalability for large-scale applications. We investigate a new solution based on a classical convex optimization framework, known as Augmented Lagrangian Methods (ALM). The new convex solvers provide a viable solution to real-world, time-critical applications such as face recognition. We conduct extensive experiments to validate and compare the performance of the ALM algorithms against several popular L1-minimization solvers, including interior-point method, Homotopy, FISTA, SESOP-PCD, approximate message passing (AMP) and TFOCS. To aid peer evaluation, the code for all the algorithms has been made publicly available.

Mohammad Keshavarzi, Michael Zollhoefer, Allen Y. Yang et al. · berkeley

Remote telepresence via next-generation mixed reality platforms can provide higher levels of immersion for computer-mediated communications, allowing participants to engage in a wide spectrum of activities, previously not possible in 2D screen-based communication methods. However, as mixed reality experiences are limited to the local physical surrounding of each user, finding a common virtual ground where users can freely move and interact with each other is challenging. In this paper, we propose a novel mutual scene synthesis method that takes the participants' spaces as input, and generates a virtual synthetic scene that corresponds to the functional features of all participants' local spaces. Our method combines a mutual function optimization module with a deep-learning conditional scene augmentation process to generate a scene mutually and physically accessible to all participants of a mixed reality telepresence scenario. The synthesized scene can hold mutual walkable, sittable and workable functions, all corresponding to physical objects in the users' real environments. We perform experiments using the MatterPort3D dataset and conduct comparative user studies to evaluate the effectiveness of our system. Our results show that our proposed approach can be a promising research direction for facilitating contextualized telepresence systems for next-generation spatial computing platforms.

Weiyu Feng, Seth Z. Zhao, Chuanyu Pan et al.

Digital twin is a problem of augmenting real objects with their digital counterparts. It can underpin a wide range of applications in augmented reality (AR), autonomy, and UI/UX. A critical component in a good digital-twin system is real-time, accurate 3D object tracking. Most existing works solve 3D object tracking through the lens of robotic grasping, employ older generations of depth sensors, and measure performance metrics that may not apply to other digital-twin applications such as in AR. In this work, we create a novel RGB-D dataset, called Digital Twin Tracking Dataset (DTTD), to enable further research of the problem and extend potential solutions towards longer ranges and mm localization accuracy. To reduce point cloud noise from the input source, we select the latest Microsoft Azure Kinect as the state-of-the-art time-of-flight (ToF) camera. In total, 103 scenes of 10 common off-the-shelf objects with rich textures are recorded, with each frame annotated with a per-pixel semantic segmentation and ground-truth object poses provided by a commercial motion capturing system. Through extensive experiments with model-level and dataset-level analysis, we demonstrate that DTTD can help researchers develop future object tracking methods and analyze new challenges. The dataset, data generation, annotation, and model evaluation pipeline are made publicly available as open source code at: https://github.com/augcog/DTTDv1.

Zixun Huang, Keling Yao, Seth Z. Zhao et al.

Robust 6DoF pose estimation with mobile devices is the foundation for applications in robotics, augmented reality, and digital twin localization. In this paper, we extensively investigate the robustness of existing RGBD-based 6DoF pose estimation methods against varying levels of depth sensor noise. We highlight that existing 6DoF pose estimation methods suffer significant performance discrepancies due to depth measurement inaccuracies. In response to the robustness issue, we present a simple and effective transformer-based 6DoF pose estimation approach called DTTDNet, featuring a novel geometric feature filtering module and a Chamfer distance loss for training. Moreover, we advance the field of robust 6DoF pose estimation and introduce a new dataset -- Digital Twin Tracking Dataset Mobile (DTTD-Mobile), tailored for digital twin object tracking with noisy depth data from the mobile RGBD sensor suite of the Apple iPhone 14 Pro. Extensive experiments demonstrate that DTTDNet significantly outperforms state-of-the-art methods at least 4.32, up to 60.74 points in ADD metrics on the DTTD-Mobile. More importantly, our approach exhibits superior robustness to varying levels of measurement noise, setting a new benchmark for robustness to measurement noise. The project page is publicly available at https://openark-berkeley.github.io/DTTDNet/.

Jesse Paterson, Jiwoong Han, Tom Cheng et al.

As the capability and complexity of UAVs continue to increase, the human-robot interface community has a responsibility to design better ways of specifying the complex 3D flight paths necessary for instructing them. Immersive interfaces, such as those afforded by virtual reality (VR), have several unique traits which may improve the user's ability to perceive and specify 3D information. These traits include stereoscopic depth cues which induce a sense of physical space as well as six degrees of freedom (DoF) natural head-pose and gesture interactions. This work introduces an open-source platform for 3D aerial path planning in VR and compares it to existing UAV piloting interfaces. Our study has found statistically significant improvements in safety and subjective usability over a manual control interface, while achieving a statistically significant efficiency improvement over a 2D touchscreen interface. The results illustrate that immersive interfaces provide a viable alternative to touchscreen interfaces for UAV path planning.

Allen Yang, Edward Yang

According to PBS, nearly one-third of Americans lack access to primary care services, and another forty percent delay going to avoid medical costs. As a result, many diseases are left undiagnosed and untreated, even if the disease shows many physical symptoms on the skin. With the rise of AI, self-diagnosis and improved disease recognition have become more promising than ever; in spite of that, existing methods suffer from a lack of large-scale patient databases and outdated methods of study, resulting in studies being limited to only a few diseases or modalities. This study incorporates readily available and easily accessible patient information via image and text for skin disease classification on a new dataset of 26 skin disease types that includes both skin disease images (37K) and associated patient narratives. Using this dataset, baselines for various image models were established that outperform existing methods. Initially, the Resnet-50 model was only able to achieve an accuracy of 70% but, after various optimization techniques, the accuracy was improved to 80%. In addition, this study proposes a novel fine-tuning strategy for sequence classification Large Language Models (LLMs), Chain of Options, which breaks down a complex reasoning task into intermediate steps at training time instead of inference. With Chain of Options and preliminary disease recommendations from the image model, this method achieves state of the art accuracy 91% in diagnosing patient skin disease given just an image of the afflicted area as well as a patient description of the symptoms (such as itchiness or dizziness). Through this research, an earlier diagnosis of skin diseases can occur, and clinicians can work with deep learning models to give a more accurate diagnosis, improving quality of life and saving lives.

Alexander Mai, Allen Yang, Dominique E. Meyer

Central to the application of many multi-view geometry algorithms is the extraction of matching points between multiple viewpoints, enabling classical tasks such as camera pose estimation and 3D reconstruction. Many approaches that characterize these points have been proposed based on hand-tuned appearance models or data-driven learning methods. We propose Soft Expectation and Deep Maximization (SEDM), an iterative unsupervised learning process that directly optimizes the repeatability of the features by posing the problem in a similar way to expectation maximization (EM). We found convergence to be reliable and the new model to be more lighting invariant and better at localize the underlying 3D points in a scene, improving SfM quality when compared to other state of the art deep learning detectors.

Mohammad Keshavarzi, Flaviano Christian Reyes, Ritika Shrivastava et al.

Indoor scene augmentation has become an emerging topic in the field of computer vision and graphics with applications in augmented and virtual reality. However, current state-of-the-art systems using deep neural networks require large datasets for training. In this paper we introduce GSACNet, a contextual scene augmentation system that can be trained with limited scene priors. GSACNet utilizes a novel parametric data augmentation method combined with a Graph Attention and Siamese network architecture followed by an Autoencoder network to facilitate training with small datasets. We show the effectiveness of our proposed system by conducting ablation and comparative studies with alternative systems on the Matterport3D dataset. Our results indicate that our scene augmentation outperforms prior art in scene synthesis with limited scene priors available.

Mohammad Keshavarzi, Oladapo Afolabi, Luisa Caldas et al.

The availability of rich 3D datasets corresponding to the geometrical complexity of the built environments is considered an ongoing challenge for 3D deep learning methodologies. To address this challenge, we introduce GenScan, a generative system that populates synthetic 3D scan datasets in a parametric fashion. The system takes an existing captured 3D scan as an input and outputs alternative variations of the building layout including walls, doors, and furniture with corresponding textures. GenScan is a fully automated system that can also be manually controlled by a user through an assigned user interface. Our proposed system utilizes a combination of a hybrid deep neural network and a parametrizer module to extract and transform elements of a given 3D scan. GenScan takes advantage of style transfer techniques to generate new textures for the generated scenes. We believe our system would facilitate data augmentation to expand the currently limited 3D geometry datasets commonly used in 3D computer vision, generative design, and general 3D deep learning tasks.

Mohammad Keshavarzi, Aakash Parikh, Xiyu Zhai et al.

Spatial computing experiences are constrained by the real-world surroundings of the user. In such experiences, augmenting virtual objects to existing scenes require a contextual approach, where geometrical conflicts are avoided, and functional and plausible relationships to other objects are maintained in the target environment. Yet, due to the complexity and diversity of user environments, automatically calculating ideal positions of virtual content that is adaptive to the context of the scene is considered a challenging task. Motivated by this problem, in this paper we introduce SceneGen, a generative contextual augmentation framework that predicts virtual object positions and orientations within existing scenes. SceneGen takes a semantically segmented scene as input, and outputs positional and orientational probability maps for placing virtual content. We formulate a novel spatial Scene Graph representation, which encapsulates explicit topological properties between objects, object groups, and the room. We believe providing explicit and intuitive features plays an important role in informative content creation and user interaction of spatial computing settings, a quality that is not captured in implicit models. We use kernel density estimation (KDE) to build a multivariate conditional knowledge model trained using prior spatial Scene Graphs extracted from real-world 3D scanned data. To further capture orientational properties, we develop a fast pose annotation tool to extend current real-world datasets with orientational labels. Finally, to demonstrate our system in action, we develop an Augmented Reality application, in which objects can be contextually augmented in real-time.

Oladapo Afolabi, Allen Y. Yang, S. Shankar Sastry

Recent advances in computer graphics and computer vision have found successful application of deep neural network models for 3D shapes based on signed distance functions (SDFs) that are useful for shape representation, retrieval, and completion. However, this approach has been limited by the need to have query shapes in the same canonical scale and pose as those observed during training, restricting its effectiveness on real world scenes. We present a formulation to overcome this issue by jointly estimating shape and similarity transform parameters. We conduct experiments to demonstrate the effectiveness of this formulation on synthetic and real datasets and report favorable comparisons to the state of the art. Finally, we also emphasize the viability of this approach as a form of 3D model compression.

Alexander Mai, Joseph Menke, Allen Yang

Image space feature detection is the act of selecting points or parts of an image that are easy to distinguish from the surrounding image region. By combining a repeatable point detection with a descriptor, parts of an image can be matched with one another, which is useful in applications like estimating pose from camera input or rectifying images. Recently, precise indoor tracking has started to become important for Augmented and Virtual reality as it is necessary to allow positioning of a headset in 3D space without the need for external tracking devices. Several modern feature detectors use homographies to simulate different viewpoints, not only to train feature detection and description, but test them as well. The problem is that, often, views of indoor spaces contain high depth disparity. This makes the approximation that a homography applied to an image represents a viewpoint change inaccurate. We claim that in order to train detectors to work well in indoor environments, they must be robust to this type of geometry, and repeatable under true viewpoint change instead of homographies. Here we focus on the problem of detecting repeatable feature locations under true viewpoint change. To this end, we generate labeled 2D images from a photo-realistic 3D dataset. These images are used for training a neural network based feature detector. We further present an algorithm for automatically generating labels of repeatable 2D features, and present a fast, easy to use test algorithm for evaluating a detector in an 3D environment.

Mohammad Keshavarzi, Allen Y. Yang, Woojin Ko et al.

Spatial computing experiences are physically constrained by the geometry and semantics of the local user environment. This limitation is elevated in remote multi-user interaction scenarios, where finding a common virtual ground physically accessible for all participants becomes challenging. Locating a common accessible virtual ground is difficult for the users themselves, particularly if they are not aware of the spatial properties of other participants. In this paper, we introduce a framework to generate an optimal mutual virtual space for a multi-user interaction setting where remote users' room spaces can have different layout and sizes. The framework further recommends movement of surrounding furniture objects that expand the size of the mutual space with minimal physical effort. Finally, we demonstrate the performance of our solution on real-world datasets and also a real HoloLens application. Results show the proposed algorithm can effectively discover optimal shareable space for multi-user virtual interaction and hence facilitate remote spatial computing communication in various collaborative workflows.

Zhijiong Huang, Yu Zhang, Kathryn C. Quigley et al.

Virtual reality (VR) is an important new technology that is fun-damentally changing the way people experience entertainment and education content. Due to the fact that most currently available VR products are one size fits all, the accessibility of the content design and user interface design, even for healthy children is not well understood. It requires more research to ensure that children can have equally good user compared to adults in VR. In our study, we seek to explore accessibility of locomotion in VR between healthy adults and minors along both objective and subjective dimensions. We performed a user experience experiment where subjects completed a simple task of moving and touching underwater animals in VR using one of four different locomotion modalities, as well as real-world walking without wearing VR headsets as the baseline. Our results show that physical body movement that mirrors real-world movement exclusively is the least preferred by both adults and minors. However, within the different modalities of controller assisted locomotion there are variations between adults and minors for preference and challenge levels.

Mohammad Keshavarzi, Michael Wu, Michael N. Chin et al.

Virtual and augmented reality communication platforms are seen as promising modalities for next-generation remote face-to-face interactions. Our study attempts to explore non-verbal communication features in relation to their conversation context for virtual and augmented reality mediated communication settings. We perform a series of user experiments, triggering nine conversation tasks in 4 settings, each containing corresponding non-verbal communication features. Our results indicate that conversation types which involve less emotional engagement are more likely to be acceptable in virtual reality and augmented reality settings with low-fidelity avatar representation, compared to scenarios that involve high emotional engagement or intellectually difficult discussions. We further systematically analyze and rank the impact of low-fidelity representation of micro-expressions, body scale, head pose, and hand gesture in affecting the user experience in one-on-one conversations, and validate that preserving micro-expression cues plays the most effective role in improving bi-directional conversations in future virtual and augmented reality settings.

Zhang Qianhao, Alexander Mai, Joseph Menke et al.

In visual Simultaneous Localization And Mapping (SLAM), detecting loop closures has been an important but difficult task. Currently, most solutions are based on the bag-of-words approach. Yet the possibility of deep neural network application to this task has not been fully explored due to the lack of appropriate architecture design and of sufficient training data. In this paper we demonstrate the applicability of deep neural networks by addressing both issues. Specifically we show that a feature pyramid Siamese neural network can achieve state-of-the-art performance on pairwise loop closure detection. The network is trained and tested on large-scale RGB-D datasets with a novel automatic loop closure labeling algorithm. Each image pair is labelled by how much the images overlap, allowing loop closure to be computed directly rather than by labor intensive manual labeling. We present an algorithm to adopt any large-scale generic RGB-D dataset for use in training deep loop-closure networks. We show for the first time that deep neural networks are capable of detecting loop closures, and we provide a method for generating large-scale datasets for use in evaluating and training loop closure detectors.

David L. McPherson, Dexter R. R. Scobee, Joseph Menke et al.

When a human supervisor collaborates with a team of robots, their attention is divided and cognitive resources are at a premium. We aim to optimize the distribution of these resources and the flow of attention. To this end, we propose the model of an idealized supervisor to describe human behavior. Such a supervisor employs a potentially inaccurate internal model of the the robots' dynamics to judge safety. We represent these safety judgements by constructing a safe set from this internal model using reachability theory. When a robot leaves this safe set, the idealized supervisor will intervene to assist, regardless of whether or not the robot remains objectively safe. False positives, where a human supervisor incorrectly judges a robot to be in danger, needlessly consume supervisor attention. In this work, we propose a method that decreases false positives by learning the supervisor's safe set and using that information to govern robot behavior. We prove that robots behaving according to our approach will reduce the occurrence of false positives for our idealized supervisor model. Furthermore, we empirically validate our approach with a user study that demonstrates a significant ($p = 0.0328$) reduction in false positives for our method compared to a baseline safety controller.

Liansheng Zhuang, Tsung-Han Chan, Allen Y. Yang et al.

Single-sample face recognition is one of the most challenging problems in face recognition. We propose a novel algorithm to address this problem based on a sparse representation based classification (SRC) framework. The new algorithm is robust to image misalignment and pixel corruption, and is able to reduce required gallery images to one sample per class. To compensate for the missing illumination information traditionally provided by multiple gallery images, a sparse illumination learning and transfer (SILT) technique is introduced. The illumination in SILT is learned by fitting illumination examples of auxiliary face images from one or more additional subjects with a sparsely-used illumination dictionary. By enforcing a sparse representation of the query image in the illumination dictionary, the SILT can effectively recover and transfer the illumination and pose information from the alignment stage to the recognition stage. Our extensive experiments have demonstrated that the new algorithms significantly outperform the state of the art in the single-sample regime and with less restrictions. In particular, the single-sample face alignment accuracy is comparable to that of the well-known Deformable SRC algorithm using multiple gallery images per class. Furthermore, the face recognition accuracy exceeds those of the SRC and Extended SRC algorithms using hand labeled alignment initialization.

Henrik Ohlsson, Allen Y. Yang, Roy Dong et al.

In many compressive sensing problems today, the relationship between the measurements and the unknowns could be nonlinear. Traditional treatment of such nonlinear relationships have been to approximate the nonlinearity via a linear model and the subsequent un-modeled dynamics as noise. The ability to more accurately characterize nonlinear models has the potential to improve the results in both existing compressive sensing applications and those where a linear approximation does not suffice, e.g., phase retrieval. In this paper, we extend the classical compressive sensing framework to a second-order Taylor expansion of the nonlinearity. Using a lifting technique and a method we call quadratic basis pursuit, we show that the sparse signal can be recovered exactly when the sampling rate is sufficiently high. We further present efficient numerical algorithms to recover sparse signals in second-order nonlinear systems, which are considerably more difficult to solve than their linear counterparts in sparse optimization.

Dheeraj Singaraju, Ehsan Elhamifar, Roberto Tron et al.

Recent results in Compressive Sensing have shown that, under certain conditions, the solution to an underdetermined system of linear equations with sparsity-based regularization can be accurately recovered by solving convex relaxations of the original problem. In this work, we present a novel primal-dual analysis on a class of sparsity minimization problems. We show that the Lagrangian bidual (i.e., the Lagrangian dual of the Lagrangian dual) of the sparsity minimization problems can be used to derive interesting convex relaxations: the bidual of the $\ell_0$-minimization problem is the $\ell_1$-minimization problem; and the bidual of the $\ell_{0,1}$-minimization problem for enforcing group sparsity on structured data is the $\ell_{1,\infty}$-minimization problem. The analysis provides a means to compute per-instance non-trivial lower bounds on the (group) sparsity of the desired solutions. In a real-world application, the bidual relaxation improves the performance of a sparsity-based classification framework applied to robust face recognition.