相关论文: Low-Light Image Enhancement via Generative Percept…

Low-light image enhancement (LLIE) is essential for numerous computer vision tasks, including object detection, tracking, segmentation, and scene understanding. Despite substantial research on improving low-quality images captured in…

Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, despite access to these tool-generated visual cues, MLLMs often fail to benefit from…

Perceptual image restoration seeks for high-fidelity images that most likely degrade to given images. For better visual quality, previous work proposed to search for solutions within the natural image manifold, by exploiting the latent…

Images captured under real-world low-light conditions face significant challenges due to uneven ambient lighting, making it difficult for existing end-to-end methods to enhance images with a large dynamic range to normal exposure levels. To…

Images captured in nighttime scenes suffer from severely reduced visibility, hindering effective content perception. Current low-light image enhancement (LLIE) methods face significant challenges: data-driven end-to-end mapping networks…

Prompt learning has been designed as an alternative to fine-tuning for adapting Vision-language (V-L) models to the downstream tasks. Previous works mainly focus on text prompt while visual prompt works are limited for V-L models. The…

In recent years, considerable research has been conducted on vision-language models that handle both image and text data; these models are being applied to diverse downstream tasks, such as "image-related chat," "image recognition by…

Vision-language (VL) Pre-training (VLP) has shown to well generalize VL models over a wide range of VL downstream tasks, especially for cross-modal retrieval. However, it hinges on a huge amount of image-text pairs, which requires tedious…

Deep learning-based methods for low-light image enhancement typically require enormous paired training data, which are impractical to capture in real-world scenarios. Recently, unsupervised approaches have been explored to eliminate the…

Achieving deep alignment between vision and language remains a central challenge for Multimodal Large Language Models (MLLMs). These models often fail to fully leverage visual input, defaulting to strong language priors. Our approach first…

Event camera has recently received much attention for low-light image enhancement (LIE) thanks to their distinct advantages, such as high dynamic range. However, current research is prohibitively restricted by the lack of large-scale,…

Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images. Most existing methods learn the mapping function between low/normal-light images by Deep Neural Networks (DNNs) on…

Low-light image enhancement aims to improve an image's visibility while keeping its visual naturalness. Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we…

Traditional preference tuning methods for LLMs/Visual Generative Models often rely solely on reward model labeling, which can be opaque, offer limited insights into the rationale behind preferences, and are prone to issues such as reward…

Low-level enhancement and high-level visual understanding in low-light vision have traditionally been treated separately. Low-light enhancement improves image quality for downstream tasks, but existing methods rely on physical or geometric…

Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the prompt quality. While recent methods show that visual…

Previous low-light image enhancement (LLIE) approaches, while employing frequency decomposition techniques to address the intertwined challenges of low frequency (e.g., illumination recovery) and high frequency (e.g., noise reduction),…

Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial…

Recent advancements in Low-Light Image Enhancement (LLIE) have focused heavily on Diffusion Probabilistic Models, which achieve high perceptual quality but suffer from significant computational latency (often exceeding 2-4 seconds per…

Image deblurring has advanced rapidly with deep learning, yet most methods exhibit poor generalization beyond their training datasets, with performance dropping significantly in real-world scenarios. Our analysis shows this limitation stems…