相关论文: 4K-Resolution Photo Exposure Correction at 125 FPS…
Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification and computer vision tasks. However, implementing optical nonlinearity is challenging,…
We propose RepMLP, a multi-layer-perceptron-style neural network building block for image recognition, which is composed of a series of fully-connected (FC) layers. Compared to convolutional layers, FC layers are more efficient, better at…
Low-light image enhancement (LLIE) aims to improve the illuminance of images due to insufficient light exposure. Recently, various lightweight learning-based LLIE methods have been proposed to handle the challenges of unfavorable prevailing…
Photometric stereo provides an important method for high-fidelity 3D reconstruction based on multiple intensity images captured under different illumination directions. In this paper, we present a complete framework, including a multilight…
Photographs taken with less-than-ideal exposure settings often display poor visual quality. Since the correction procedures vary significantly, it is difficult for a single neural network to handle all exposure problems. Moreover, the…
Recently, numerous algorithms have been developed to tackle the problem of light field super-resolution (LFSR), i.e., super-resolving low-resolution light fields to gain high-resolution views. Despite delivering encouraging results, these…
Deep neural network models have a complex architecture and are overparameterized. The number of parameters is more than the whole dataset, which is highly resource-consuming. This complicates their application and limits its usage on…
Rectifying the orientation of images represents a daily task for every photographer. This task may be complicated even for the human eye, especially when the horizon or other horizontal and vertical lines in the image are missing. In this…
Recently, several models based on deep neural networks have achieved great success in terms of both reconstruction accuracy and computational performance for single image super-resolution. In these methods, the low resolution (LR) input…
Light field imaging is limited in its computational processing demands of high sampling for both spatial and angular dimensions. Single-shot light field cameras sacrifice spatial resolution to sample angular viewpoints, typically by…
Recent years have witnessed the great advances of deep neural networks (DNNs) in light field (LF) image super-resolution (SR). However, existing DNN-based LF image SR methods are developed on a single fixed degradation (e.g., bicubic…
Image super-resolution (SR) in resource-constrained scenarios demands lightweight models balancing performance and latency. Convolutional neural networks (CNNs) offer low latency but lack non-local feature capture, while Transformers excel…
Images acquired in low-light environments present significant obstacles for computer vision systems and human perception, especially for applications requiring accurate object recognition and scene analysis. Such images typically manifest…
Deep convolutional neural networks can enhance images taken with small mobile camera sensors and excel at tasks like demoisaicing, denoising and super-resolution. However, for practical use on mobile devices these networks often require too…
2D Gaussian Splatting (2DGS) is an emerging explicit scene representation method with significant potential for image compression due to high fidelity and high compression ratios. However, existing low-light enhancement algorithms operate…
Recent advances in extreme image compression have revealed that mapping pixel data into highly compact latent representations can significantly improve coding efficiency. However, most existing methods compress images into 2-D latent spaces…
Low-Light Image Enhancement (LLIE) is a key task in computational photography and imaging. The problem of enhancing images captured during night or in dark environments has been well-studied in the computer vision literature. However,…
Image tokenization has significantly advanced visual generation and multimodal modeling, particularly when paired with autoregressive models. However, current methods face challenges in balancing efficiency and fidelity: high-resolution…
We present a technique for the estimation of photometric redshifts based on feed-forward neural networks. The Multilayer Perceptron (MLP) Artificial Neural Network is used to predict photometric redshifts in the HDF-S from an ultra deep…
Due to the factors like processing power limitations and channel capabilities images are often down sampled and transmitted at low bit rates resulting in a low resolution compressed image. High resolution images can be reconstructed from…