Related papers: VCR: Variance-Driven Channel Recalibration for Rob…
Low light very likely leads to the degradation of an image's quality and even causes visual task failures. Existing image enhancement technologies are prone to overenhancement, color distortion or time consumption, and their adaptability is…
Although Visual-Language Models (VLMs) have shown impressive capabilities in tasks like visual question answering and image captioning, they still struggle with hallucinations. Analysis of attention distribution in these models shows that…
Vector quantised variational autoencoders (VQ-VAE) are characterised by three main components: 1) encoding visual data, 2) assigning $k$ different vectors in the so-called embedding space, and 3) decoding the learnt features. While images…
Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned. Despite their success, LVLMs still…
Visible Light Communication (VLC) is emerging as a means to network computing devices that ameliorates many hurdles of radio-frequency (RF) communications, for example, the limited available spectrum. Enabling VLC in wearable computing,…
Depth estimation from a single image is an active research topic in computer vision. The most accurate approaches are based on fully supervised learning models, which rely on a large amount of dense and high-resolution (HR) ground-truth…
Visible Light Communication (VLC) offers a promising solution to satisfy the increasing demand for wireless data. However, link blockages remain a significant challenge. This paper addresses this issue by investigating the combined use of…
The achievable data rate in indoor wireless systems that employ visible light communication (VLC) can be limited by multipath propagation. Here, we use computer generated holograms (CGHs) in VLC system design to improve the achievable…
This paper presents a new approach for contrast enhancement of spinal cord medical images based on multirate scheme incorporated into multiscale retinex algorithm. The proposed work here uses HSV color space, since HSV color space separates…
Vision-language models (VLMs), such as CLIP, have demonstrated exceptional generalization capabilities and can quickly adapt to downstream tasks through prompt fine-tuning. Unfortunately, in classification tasks involving non-training…
HEVC includes a Coding Unit (CU) level luminance-based perceptual quantization technique known as AdaptiveQP. AdaptiveQP perceptually adjusts the Quantization Parameter (QP) at the CU level based on the spatial activity of raw input video…
This paper presents a comprehensive survey of computational imaging (CI) techniques and their transformative impact on computer vision (CV) applications. Conventional imaging methods often fail to deliver high-fidelity visual data in…
Multi-Channel Imaging (MCI) contains an array of challenges for encoding useful feature representations not present in traditional images. For example, images from two different satellites may both contain RGB channels, but the remaining…
Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to…
Low-light RAW video denoising is a fundamentally challenging task due to severe signal degradation caused by high sensor gain and short exposure times, which are inherently limited by video frame rate requirements. To address this, we…
This paper presents a framework for developing a live vision-correcting display (VCD) to address refractive visual aberrations without the need for traditional vision correction devices like glasses or contact lenses, particularly in…
In this paper, we propose a luminance-guided chrominance image enhancement convolutional neural network for HEVC intra coding. Specifically, we firstly develop a gated recursive asymmetric-convolution block to restore each degraded…
The Variational Autoencoder (VAE) is known to suffer from the phenomenon of \textit{posterior collapse}, where the latent representations generated by the model become independent of the inputs. This leads to degenerated representations of…
We introduce LTCF-Net, a novel network architecture designed for enhancing low-light images. Unlike Retinex-based methods, our approach utilizes two color spaces - LAB and YUV - to efficiently separate and process color information, by…
Self-attention and transformer architectures have become foundational components in modern deep learning. Recent efforts have integrated transformer blocks into compact neural architectures for computer vision, giving rise to various…