Related papers: Deep Unfolded BM3D: Unrolling Non-local Collaborat…

Computed tomography (CT) is indispensable for clinical diagnosis and image-guided interventions but exposes patients to ionizing radiation, motivating the development of safer imaging alternatives. Ultrasound (US) is non-ionizing and widely…

Deep learning for decoding EEG signals has gained traction, with many claims to state-of-the-art accuracy. However, despite the convincing benchmark performance, successful translation to real applications is limited. The frequent…

In massive multiple-input multiple-output (MIMO) systems, hybrid analog-digital (AD) beamforming can be used to attain a high directional gain without requiring a dedicated radio frequency (RF) chain for each antenna element, which…

Traditional model-based image reconstruction (MBIR) methods combine forward and noise models with simple object priors. Recent application of deep learning methods for image reconstruction provides a successful data-driven approach to…

Multispectral computed tomography (CT) enables advanced material characterization by acquiring energy-resolved projection data. However, since the incoming X-ray flux is be distributed across multiple narrow energy bins, the photon count…

While neural networks have achieved vastly enhanced performance over traditional iterative methods in many cases, they are generally empirically designed and the underlying structures are difficult to interpret. The algorithm unrolling…

Transformers have shown significant success in hyperspectral unmixing (HU). However, challenges remain. While multi-scale and long-range spatial correlations are essential in unmixing tasks, current Transformer-based unmixing networks,…

The performance of Federated learning (FL) is negatively affected by device differences and statistical characteristics between participating clients. To address this issue, we introduce a deep unfolding network (DUN)-based technique that…

To ease the difficulty of acquiring annotation labels in 3D data, a common method is using unsupervised and open-vocabulary semantic segmentation, which leverage 2D CLIP semantic knowledge. In this paper, unlike previous research that…

Self-supervised denoising has attracted widespread attention due to its ability to train without clean images. However, noise in real-world scenarios is often spatially correlated, which causes many self-supervised algorithms that assume…

Depth from defocus (DfD) and stereo matching are two most studied passive depth sensing schemes. The techniques are essentially complementary: DfD can robustly handle repetitive textures that are problematic for stereo matching whereas…

Model-based methods and deep neural networks have both been tremendously successful paradigms in machine learning. In model-based methods, problem domain knowledge can be built into the constraints of the model, typically at the expense of…

Like masked language modeling (MLM) in natural language processing, masked image modeling (MIM) aims to extract valuable insights from image patches to enhance the feature extraction capabilities of the underlying deep neural network (DNN).…

Digital Breast Tomosynthesis (DBT) enhances finding visibility for breast cancer detection by providing volumetric information that reduces the impact of overlapping tissues; however, limited annotated data has constrained the development…

In this paper, we explore a critical yet under-investigated issue: how to learn robust and well-generalized 3D representation from pre-trained vision language models such as CLIP. Previous works have demonstrated that cross-modal…

Recently developed deep-learning-based denoisers often outperform state-of-the-art conventional denoisers such as the BM3D. They are typically trained to minimize the mean squared error (MSE) between the output image of a deep neural…

Mapping and 3D detection are two major issues in vision-based robotics, and self-driving. While previous works only focus on each task separately, we present an innovative and efficient multi-task deep learning framework (SM3D) for…

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the…

Machine Learning Interatomic Potentials (MLIPs) have successfully demonstrated scaling behavior, i.e. the power-law improvement in training performance, however the emergence of novel capabilities at scale remains unexplored. We have…

Recently, deep neural networks (DNNs) have been regarded as the state-of-the-art classification methods in a wide range of applications, especially in image classification. Despite the success, the huge number of parameters blocks its…