相关论文: Bringing Linearly Transformed Cosines to Anisotrop…

Token-based transformer world models have shown strong performance in visual reinforcement learning, but often suffer from temporal inconsistency in long-horizon rollouts, including object duplication, disappearance, and transmutation. A…

Graph contrastive learning (GCL) has become a hot topic in the field of graph representation learning. In contrast to traditional supervised learning relying on a large number of labels, GCL exploits augmentation strategies to generate…

Image matching that finding robust and accurate correspondences across images is a challenging task under extreme conditions. Capturing local and global features simultaneously is an important way to mitigate such an issue but recent…

Correlated time series (CTS) forecasting plays an essential role in many practical applications, such as traffic management and server load control. Many deep learning models have been proposed to improve the accuracy of CTS forecasting.…

Real-time global illumination is key to enabling more dynamic and physically realistic worlds in performance-critical applications such as games or any other applications with real-time constraints.Hardware-accelerated ray tracing in modern…

Understanding the geometry of neural network loss landscapes is a central question in deep learning, with implications for generalization and optimization. A striking phenomenon is linear mode connectivity (LMC), where independently trained…

Conceptual studies and numerical simulations are performed for imaging devices that transform a near-field pattern into magnified far-zone images and are based on high-order spatial transformation in cylindrical domains. A lens translating…

Image cartoonization is recently dominated by generative adversarial networks (GANs) from the perspective of unsupervised image-to-image translation, in which an inherent challenge is to precisely capture and sufficiently transfer…

Dynamic reconstruction has achieved remarkable progress, but there remain challenges in monocular input for more practical applications. The prevailing works attempt to construct efficient motion representations, but lack a unified…

In this paper, we introduce a new nonlinear optical channel equalizer based on Transformers. By leveraging parallel computation and attending directly to the memory across a sequence of symbols, we show that Transformers can be used…

Graph Transformers (GTs) have made remarkable achievements in graph-level tasks. However, most existing works regard graph structures as a form of guidance or bias for enhancing node representations, which focuses on node-central…

Global illumination (GI) is essential for realistic rendering but remains computationally expensive due to the complexity of simulating indirect light transport. Recent neural methods have mainly relied on per-scene optimization, sometimes…

Voxel representation and processing is an important issue in a broad spectrum of applications. E.g., 3D imaging in biomedical engineering applications, video game development and volumetric displays are often based on data representation by…

Under-approximations of reachable sets and tubes have been receiving growing research attention due to their important roles in control synthesis and verification. Available under-approximation methods applicable to continuous-time linear…

Recently, several approaches have emerged for generating neural representations with multiple levels of detail (LODs). LODs can improve the rendering by using lower resolutions and smaller model sizes when appropriate. However, existing…

Most of cosmological observables are light-propagated. I will present coordinates adapted to the propagation of null-like signals as observed by a geodesic observer. These "geodesic light-cone (GLC) coordinates" are general, adapted to…

Numerical solutions of hyperbolic partial differential equations(PDEs) are ubiquitous in science and engineering. Method of lines is a popular approach to discretize PDEs defined in spacetime, where space and time are discretized…

Despite recent advances in lane detection methods, scenarios with limited- or no-visual-clue of lanes due to factors such as lighting conditions and occlusion remain challenging and crucial for automated driving. Moreover, current lane…

Global backprojection-convolution (GBC) is a recently developed theory for exact reconstruction in transmission cone-beam computed tomography (CBCT). It is the first exact inversion theory that applies when the X-ray source points comprise…

We present TransLPC, a novel detection model for large point clouds that is based on a transformer architecture. While object detection with transformers has been an active field of research, it has proved difficult to apply such models to…