Generating font glyphs of consistent style from one or a few reference glyphs, i.e., font completion, is an important task in topographical design. As the problem is more well-defined than general image style transfer tasks, thus it has received inte
rest from both vision and machine learning communities. Existing approaches address this problem as a direct image-to-image translation task. In this work, we innovate to explore the generation of font glyphs as 2D graphic objects with the graph as an intermediate representation, so that more intrinsic graphic properties of font styles can be captured. Specifically, we formulate a cross-modality cycled image-to-image model structure with a graph constructor between an image encoder and an image renderer. The novel graph constructor maps a glyphs latent code to its graph representation that matches expert knowledge, which is trained to help the translation task. Our model generates improved results than both image-to-image baseline and previous state-of-the-art methods for glyph completion. Furthermore, the graph representation output by our model also provides an intuitive interface for users to do local editing and manipulation. Our proposed cross-modality cycled representation learning has the potential to be applied to other domains with prior knowledge from different data modalities. Our code is available at https://github.com/VITA-Group/Font_Completion_Graph.
Combining X-ray tomography with simultaneous shear force measurement, we investigate shear-induced granular avalanches using spherical particles with different surface roughness. We find that systems consisting of particles with large surface roughne
ss display quasi-periodic avalanches interrupted by crackling-like small ones. In contrast, systems consisting of particles with small roughness display no detectable avalanches. The stress drop of quasi-periodic avalanche shows a linear relation with the correlation length of particle non-affine displacement, suggesting that roughness enhances inter-particle locking and hence particle-level dynamic correlation length. However, the nonaffine displacement is two orders of magnitude smaller than particle size, indicating that stress is mainly released on the length scale of roughness. The correlation length of non-affine displacements abruptly increases when a quasi-periodic avalanche occurs, suggesting that quasi-periodic avalanches can be interpreted as a spinodal nucleation event in a first-order phase transition.
Generative adversarial networks (GANs) nowadays are capable of producing images of incredible realism. One concern raised is whether the state-of-the-art GANs learned distribution still suffers from mode collapse, and what to do if so. Existing diver
sity tests of samples from GANs are usually conducted qualitatively on a small scale, and/or depends on the access to original training data as well as the trained model parameters. This paper explores to diagnose GAN intra-mode collapse and calibrate that, in a novel black-box setting: no access to training data, nor the trained model parameters, is assumed. The new setting is practically demanded, yet rarely explored and significantly more challenging. As a first stab, we devise a set of statistical tools based on sampling, that can visualize, quantify, and rectify intra-mode collapse. We demonstrate the effectiveness of our proposed diagnosis and calibration techniques, via extensive simulations and experiments, on unconditional GAN image generation (e.g., face and vehicle). Our study reveals that the intra-mode collapse is still a prevailing problem in state-of-the-art GANs and the mode collapse is diagnosable and calibratable in black-box settings. Our codes are available at: https://github.com/VITA-Group/BlackBoxGANCollapse.
Federated learning enables a large number of clients to participate in learning a shared model while maintaining the training data stored in each client, which protects data privacy and security. Till now, federated learning frameworks are built in a
centralized way, in which a central client is needed for collecting and distributing information from every other client. This not only leads to high communication pressure at the central client, but also renders the central client highly vulnerable to failure and attack. Here we propose a principled decentralized federated learning algorithm (DeFed), which removes the central client in the classical Federated Averaging (FedAvg) setting and only relies information transmission between clients and their local neighbors. The proposed DeFed algorithm is proven to reach the global minimum with a convergence rate of $O(1/T)$ when the loss function is smooth and strongly convex, where $T$ is the number of iterations in gradient descent. Finally, the proposed algorithm has been applied to a number of toy examples to demonstrate its effectiveness.
Outdoor scene relighting is a challenging problem that requires good understanding of the scene geometry, illumination and albedo. Current techniques are completely supervised, requiring high quality synthetic renderings to train a solution. Such ren
derings are synthesized using priors learned from limited data. In contrast, we propose a self-supervised approach for relighting. Our approach is trained only on corpora of images collected from the internet without any user-supervision. This virtually endless source of training data allows training a general relighting solution. Our approach first decomposes an image into its albedo, geometry and illumination. A novel relighting is then produced by modifying the illumination parameters. Our solution capture shadow using a dedicated shadow prediction map, and does not rely on accurate geometry estimation. We evaluate our technique subjectively and objectively using a new dataset with ground-truth relighting. Results show the ability of our technique to produce photo-realistic and physically plausible results, that generalizes to unseen scenes.
In this paper, we investigate the photon sphere, shadow radius and quasinormal modes of a charged black hole in presence of quintessence. The result shows that the shadow radius decreases with the increase of the electric charge. The quasinormal mode
s are derived by the sixth WKB approximation method and shadow radius, respectively. For the fixed electric charge and multipole number, the values of the real and imaginary parts of the quasinormal modes decrease with the increase of the quintessence charge. When the value of the multipole number is large, the quasinormal modes derived by the two methods are consistent, which shows the correspondence between the quasinormal modes in the eikonal limit and shadow. When the value of the multipole number is small, the quasinormal modes obtained by the two methods are also in good agreement.
We propose a method for object-aware 3D egocentric pose estimation that tightly integrates kinematics modeling, dynamics modeling, and scene object information. Unlike prior kinematics or dynamics-based approaches where the two components are used di
sjointly, we synergize the two approaches via dynamics-regulated training. At each timestep, a kinematic model is used to provide a target pose using video evidence and simulation state. Then, a prelearned dynamics model attempts to mimic the kinematic pose in a physics simulator. By comparing the pose instructed by the kinematic model against the pose generated by the dynamics model, we can use their misalignment to further improve the kinematic model. By factoring in the 6DoF pose of objects (e.g., chairs, boxes) in the scene, we demonstrate for the first time, the ability to estimate physically-plausible 3D human-object interactions using a single wearable camera. We evaluate our egocentric pose estimation method in both controlled laboratory settings and real-world scenarios.
Diffusion-weighted (DW) magnetic resonance imaging is essential for the diagnosis and treatment of ischemic stroke. DW images (DWIs) are usually acquired in multi-slice settings where lesion areas in two consecutive 2D slices are highly discontinuous
due to large slice thickness and sometimes even slice gaps. Therefore, although DWIs contain rich 3D information, they cannot be treated as regular 3D or 2D images. Instead, DWIs are somewhere in-between (or 2.5D) due to the volumetric nature but inter-slice discontinuities. Thus, it is not ideal to apply most existing segmentation methods as they are designed for either 2D or 3D images. To tackle this problem, we propose a new neural network architecture tailored for segmenting highly-discontinuous 2.5D data such as DWIs. Our network, termed LambdaUNet, extends UNet by replacing convolutional layers with our proposed Lambda+ layers. In particular, Lambda+ layers transform both intra-slice and inter-slice context around a pixel into linear functions, called lambdas, which are then applied to the pixel to produce informative 2.5D features. LambdaUNet is simple yet effective in combining sparse inter-slice information from adjacent slices while also capturing dense contextual features within a single slice. Experiments on a unique clinical dataset demonstrate that LambdaUNet outperforms existing 3D/2D image segmentation methods including recent variants of UNet. Code for LambdaUNet will be released with the publication to facilitate future research.
Accurate estimation of 3D human motion from monocular video requires modeling both kinematics (body motion without physical forces) and dynamics (motion with physical forces). To demonstrate this, we present SimPoE, a Simulation-based approach for 3D
human Pose Estimation, which integrates image-based kinematic inference and physics-based dynamics modeling. SimPoE learns a policy that takes as input the current-frame pose estimate and the next image frame to control a physically-simulated character to output the next-frame pose estimate. The policy contains a learnable kinematic pose refinement unit that uses 2D keypoints to iteratively refine its kinematic pose estimate of the next frame. Based on this refined kinematic pose, the policy learns to compute dynamics-based control (e.g., joint torques) of the character to advance the current-frame pose estimate to the pose estimate of the next frame. This design couples the kinematic pose refinement unit with the dynamics-based control generation unit, which are learned jointly with reinforcement learning to achieve accurate and physically-plausible pose estimation. Furthermore, we propose a meta-control mechanism that dynamically adjusts the characters dynamics parameters based on the character state to attain more accurate pose estimates. Experiments on large-scale motion datasets demonstrate that our approach establishes the new state of the art in pose accuracy while ensuring physical plausibility.
Predicting accurate future trajectories of multiple agents is essential for autonomous systems, but is challenging due to the complex agent interaction and the uncertainty in each agents future behavior. Forecasting multi-agent trajectories requires
modeling two key dimensions: (1) time dimension, where we model the influence of past agent states over future states; (2) social dimension, where we model how the state of each agent affects others. Most prior methods model these two dimensions separately, e.g., first using a temporal model to summarize features over time for each agent independently and then modeling the interaction of the summarized features with a social model. This approach is suboptimal since independent feature encoding over either the time or social dimension can result in a loss of information. Instead, we would prefer a method that allows an agents state at one time to directly affect another agents state at a future time. To this end, we propose a new Transformer, AgentFormer, that jointly models the time and social dimensions. The model leverages a sequence representation of multi-agent trajectories by flattening trajectory features across time and agents. Since standard attention operations disregard the agent identity of each element in the sequence, AgentFormer uses a novel agent-aware attention mechanism that preserves agent identities by attending to elements of the same agent differently than elements of other agents. Based on AgentFormer, we propose a stochastic multi-agent trajectory prediction model that can attend to features of any agent at any previous timestep when inferring an agents future position. The latent intent of all agents is also jointly modeled, allowing the stochasticity in one agents behavior to affect other agents. Our method significantly improves the state of the art on well-established pedestrian and autonomous driving datasets.
