Related papers: Rethinking Model Redundancy for Low-light Image En…
Diffusion models (DMs) have gained prominence due to their ability to generate high-quality varied images with recent advancements in text-to-image generation. The research focus is now shifting towards the controllability of DMs. A…
Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images. While L1 and L2 losses are perhaps the most widely used functions for this purpose, they do not necessarily lead…
Existing unpaired low-light image enhancement approaches prefer to employ the two-way GAN framework, in which two CNN generators are deployed for enhancement and degradation separately. However, such data-driven models ignore the inherent…
Recently, Multimodal Large Language Models (MLLMs) have demonstrated significant potential in complex visual tasks through the integration of Chain-of-Thought (CoT) reasoning. However, in Video Question Answering, extended thinking…
This study introduces a novel data augmentation technique, ADLDA, aimed at mitigating the negative impact of data distribution shifts caused by the data augmentation process in computer vision task. ADLDA partitions augmented data into…
While Retrieval Augmented Generation (RAG) has emerged as a popular technique for improving Large Language Model (LLM) systems, it introduces a large number of choices, parameters and hyperparameters that must be made or tuned. This…
Euler's elastica model has been extensively studied and applied to image processing tasks. However, due to the high nonlinearity and nonconvexity of the involved curvature term, conventional algorithms suffer from slow convergence and high…
Low light conditions significantly degrade Unmanned Aerial Vehicles (UAVs) performance in critical applications. Existing Low-light Image Enhancement (LIE) methods struggle with the unique challenges of aerial imagery, including Ultra-High…
Learned image compression (LIC) using deep learning architectures has seen significant advancements, yet standard rate-distortion (R-D) optimization often encounters imbalanced updates due to diverse gradients of the rate and distortion…
While latent diffusion models (LDMs), such as Stable Diffusion, are designed for high-resolution (HR) image generation, they often struggle with significant structural distortions when generating images at resolutions higher than their…
AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature distribution changes may degrade the performance of AI models…
As vision based perception methods are usually built on the normal light assumption, there will be a serious safety issue when deploying them into low light environments. Recently, deep learning based methods have been proposed to enhance…
Current Multimodal Large Language Model (MLLM) architectures face a critical tradeoff between performance and efficiency: decoder-only architectures achieve higher performance but lower efficiency, while cross-attention-based architectures…
Tagging is nowadays the most prevalent and practical way to make images searchable. However, in reality many manually-assigned tags are irrelevant to image content and hence are not reliable for applications. A lot of recent efforts have…
Large language models (LLMs) suffer from catastrophic forgetting in sequential multi-task learning. Existing parameter regularization methods (e.g., O-LoRA, N-LoRA) mitigate interference via low-rank subspace orthogonality, but additive…
Retinex model has been applied to low-light image enhancement in many existing methods. More appropriate decomposition of a low-light image can help achieve better image enhancement. In this paper, we propose a new pixel-level non-local…
Image quality is a critical factor in delivering visually appealing content on web platforms. However, images often suffer from degradation due to lossy operations applied by online social networks (OSNs), negatively affecting user…
Post-training for large language models (LLMs) is constrained by the high cost of acquiring new knowledge or correcting errors and by the unintended side effects that frequently arise from retraining. To address these issues, we introduce…
Image enhancement is a common technique used to mitigate issues such as severe noise, low brightness, low contrast, and color deviation in low-light images. However, providing an optimal high-light image as a reference for low-light image…
When evaluating the performance of a pre-trained model transferred to a downstream task, it is imperative to assess not only the in-distribution (ID) accuracy of the downstream model but also its capacity to generalize and identify…