Related papers: Deep Amended Gradient Descent for Efficient Spectr…
Hyperspectral image (HSI) denoising is an essential procedure for HSI applications. Unfortunately, the existing Transformer-based methods mainly focus on non-local modeling, neglecting the importance of locality in image denoising.…
While recent deep neural networks have achieved promising results for 3D reconstruction from a single-view image, these rely on the availability of RGB textures in images and extra information as supervision. In this work, we propose novel…
Recent image restoration methods can be broadly categorized into two classes: (1) regression methods that recover the rough structure of the original image without synthesizing high-frequency details and (2) generative methods that…
MRI is an inherently slow process, which leads to long scan time for high-resolution imaging. The speed of acquisition can be increased by ignoring parts of the data (undersampling). Consequently, this leads to the degradation of image…
Deep neural networks face many problems in the field of hyperspectral image classification, lack of effective utilization of spatial spectral information, gradient disappearance and overfitting as the model depth increases. In order to…
Fine-detailed reconstructions are in high demand in many applications. However, most of the existing RGB-D reconstruction methods rely on pre-calculated accurate camera poses to recover the detailed surface geometry, where the…
We present a technique for developing a network of re-used features, where the topology is formed using a coarse learning method, that allows gradient-descent fine tuning, known as an Abstract Deep Network (ADN). New features are built…
We present a general learning-based solution for restoring images suffering from spatially-varying degradations. Prior approaches are typically degradation-specific and employ the same processing across different images and different pixels…
Integrating deep learning techniques into the video coding framework gains significant improvement compared to the standard compression techniques, especially applying super-resolution (up-sampling) to down-sampling based video coding as…
Image restoration algorithms such as super resolution (SR) are indispensable pre-processing modules for object detection in degraded images. However, most of these algorithms assume the degradation is fixed and known a priori. When the real…
Recent years have witnessed substantial advancements in the field of 3D reconstruction from 2D images, particularly following the introduction of the neural radiance field (NeRF) technique. However, reconstructing a 3D high dynamic range…
3D reconstruction from a single RGB image is a challenging problem in computer vision. Previous methods are usually solely data-driven, which lead to inaccurate 3D shape recovery and limited generalization capability. In this work, we focus…
In this paper, an efficient super-resolution (SR) method based on deep convolutional neural network (CNN) is proposed, namely Gradual Upsampling Network (GUN). Recent CNN based SR methods often preliminarily magnify the low resolution (LR)…
We present a simple, efficient, and scalable unfolding network, SAUNet, to simplify the network design with an adaptive alternate optimization framework for hyperspectral image (HSI) reconstruction. SAUNet customizes a Residual Adaptive…
Variational method and deep learning method are two mainstream powerful approaches to solve inverse problems in computer vision. To take advantages of advanced optimization algorithms and powerful representation ability of deep neural…
Super-resolution reconstruction techniques entail the utilization of software algorithms to transform one or more sets of low-resolution images captured from the same scene into high-resolution images. In recent years, considerable…
High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. Due to the high costs associated with HDR imaging, the literature offers various data-driven methods for HDR image reconstruction…
We study the complexity of training neural network models with one hidden nonlinear activation layer and an output weighted sum layer. We analyze Gradient Descent applied to learning a bounded target function on $n$ real-valued inputs. We…
Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vision system. Recent generative adversarial network (GAN)…
Low-altitude Gaussian splatting (LAGS) facilitates 3D scene reconstruction by aggregating aerial images from distributed drones. However, as LAGS prioritizes maximizing reconstruction quality over communication throughput, existing…