Related papers: Compression of phase-only holograms with JPEG stan…
In this paper, we investigate the counter-forensic effects of the new JPEG AI standard based on neural image compression, focusing on two critical areas: deepfake image detection and image splicing localization. Neural image compression…
Lossy compression introduces complex compression artifacts, particularly the blocking artifacts, ringing effects and blurring. Existing algorithms either focus on removing blocking artifacts and produce blurred output, or restores sharpened…
In this paper, we propose a scalable image compression scheme, including the base layer for feature representation and enhancement layer for texture representation. More specifically, the base layer is designed as the deep learning feature…
The standard JPEG format is almost the optimum format in image compression. The compression ratio in JPEG sometimes reaches 30:1. The compression ratio of JPEG could be increased by embedding the Five Modulus Method (FMM) into the JPEG…
We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation. The JPEG algorithm significantly quantizes discrete cosine transform (DCT) spectra to achieve a…
Side-informed steganography has always been among the most secure approaches in the field. However, a majority of existing methods for JPEG images use the side information, here the rounding error, in a heuristic way. For the first time, we…
High dynamic range (HDR) capture and display have seen significant growth in popularity driven by the advancements in technology and increasing consumer demand for superior image quality. As a result, HDR image compression is crucial to…
Light field (LF) imaging has gained significant attention due to its recent success in 3-dimensional (3D) displaying and rendering as well as augmented and virtual reality usage. Nonetheless, because of the two extra dimensions, LFs are…
We propose a novel JPEG XT image compression with hue compensation for two-layer HDR coding. LDR images produced from JPEG XT bitstreams have some distortion in hue due to tone mapping operations. In order to suppress the color distortion,…
High dynamic range (HDR) imaging is an indispensable technique in modern photography. Traditional methods focus on HDR reconstruction from multiple images, solving the core problems of image alignment, fusion, and tone mapping, yet having a…
Learning-based image compression methods have improved in recent years and started to outperform traditional codecs. However, neural-network approaches can unexpectedly introduce visual artifacts in some images. We therefore propose methods…
Among applications of deep learning (DL) involving low cost sensors, remote image classification involves a physical channel that separates edge sensors and cloud classifiers. Traditional DL models must be divided between an encoder for the…
Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial…
Deep learning techniques have revolutionized the fields of image restoration and image quality assessment in recent years. While image restoration methods typically utilize synthetically distorted training data for training, deep quality…
Light field photography has been studied thoroughly in recent years. One of its drawbacks is the need for multi-lens in the imaging. To compensate that, compressed light field photography has been proposed to tackle the trade-offs between…
Modern MRI schemes, which rely on compressed sensing or deep learning algorithms to recover MRI data from undersampled multichannel Fourier measurements, are widely used to reduce scan time. The image quality of these approaches is heavily…
In this study, we reveal that the interaction between haze degradation and JPEG compression introduces complex joint loss effects, which significantly complicate image restoration. Existing dehazing models often neglect compression effects,…
Traditional feature-based image stitching technologies rely heavily on feature detection quality, often failing to stitch images with few features or low resolution. The learning-based image stitching solutions are rarely studied due to the…
Recent expansions in multimedia devices gather enormous amounts of real-time images for processing and inference. The images are first compressed using compression schemes, like JPEG, to reduce storage costs and power for transmitting the…
Deep learning models have grown increasingly complex, with input data sizes scaling accordingly. Despite substantial advances in specialized deep learning hardware, data loading continues to be a major bottleneck that limits training and…