Related papers: TDIP: Tunable Deep Image Processing, a Real Time M…
This paper discusses recent research that aims to enable computation close to data, an approach we broadly call processing-in-memory (PIM). PIM places computation mechanisms in or near where the data is stored (i.e., inside memory chips or…
Decreasing sequence length is a common way to accelerate transformers, but prior token reduction work often targets classification and reports proxy metrics rather than end-to-end latency. For semantic segmentation, token reduction is…
This paper presents a model predictive control (MPC) for dynamic systems whose nonlinearity and uncertainty are modelled by deep neural networks (NNs), under input and state constraints. Since the NN output contains a high-order complex…
Automatic image matting (AIM) refers to estimating the soft foreground from an arbitrary natural image without any auxiliary input like trimap, which is useful for image editing. Prior methods try to learn semantic features to aid the…
Digital Twins are part of the vision of Industry 4.0 to represent, control, predict, and optimize the behavior of Cyber-Physical Production Systems (CPPSs). These CPPSs are long-living complex systems deployed to and configured for diverse…
In the biomedical environment, experiments assessing dynamic processes are primarily performed by a human acquisition supervisor. Contemporary implementations of such experiments frequently aim to acquire a maximum number of relevant events…
Existing permutation-invariant methods can be divided into two categories according to the aggregation scope, i.e. global aggregation and local one. Although the global aggregation methods, e. g., PointNet and Deep Sets, get involved in…
Modern robotic manipulation primarily relies on visual observations in a 2D color space for skill learning but suffers from poor generalization. In contrast, humans, living in a 3D world, depend more on physical properties-such as distance,…
Laser Metal Deposition with Powder (LMDp) is an additive manufacturing technique used for repairing metal components or producing parts with intricate geometries. However, a comprehensive understanding of the melt pool dynamics, which…
Discovering atom-level phenomena requires molecular dynamics (MD) simulations with ab initio accuracy. Machine learning interatomic potentials (MLIPs) enable stable, high-accuracy MD simulations, and their models exhibit scaling-law trends…
This article proposes a novel high-performance computing approach for the prediction of the temperature field in powder bed fusion (PBF) additive manufacturing processes. In contrast to many existing approaches to part-scale simulations,…
Machine learning (ML)-based cyber-physical systems (CPSs) have been extensively developed to improve the print quality of additive manufacturing (AM). However, the reproducibility of these systems, as presented in published research, has…
Understanding the thermal behavior of additive manufacturing (AM) processes is crucial for enhancing the quality control and enabling customized process design. Most purely physics-based computational models suffer from intensive…
This book chapter reviews progress in crystallographic image processing (CIP) for scanning probe microscopy (SPM) that has occurred since our description of the technique was first put into open access in this book series in the year 2010.…
Pretrained diffusion models (DMs) have recently been popularly used in solving inverse problems (IPs). The existing methods mostly interleave iterative steps in the reverse diffusion process and iterative steps to bring the iterates closer…
Advances in endoscopy use in surgeries face challenges like inadequate lighting. Deep learning, notably the Denoising Diffusion Probabilistic Model (DDPM), holds promise for low-light image enhancement in the medical field. However, DDPMs…
Unsupervised deep image prior (DIP) addresses shortcomings of training data requirements and limited generalization associated with supervised deep learning. The performance of DIP depends on the network architecture and the stopping point…
Image pyramids are commonly used in modern computer vision tasks to obtain multi-scale features for precise understanding of images. However, image pyramids process multiple resolutions of images using the same large-scale model, which…
Achieving fast and continuous fabrication of large-scale complex 3D structures is key to unlocking industrial-scale adoption of two-photon lithography (TPL). Despite substantial improvement in peak optical patterning rates enabled by recent…
Digital electronics is a technological cornerstone in our modern society which has covered the increasing demand in computing power during the last decades thanks to a periodic doubling of transistor density and power efficiency in…