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

We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through…

Imaging in low-light environments is challenging due to reduced scene radiance, which leads to elevated sensor noise and reduced color saturation. Most learning-based low-light enhancement methods rely on paired training data captured under…

Low-light image enhancement (LLIE) is critical in computer vision. Existing LLIE methods often fail to discover the underlying relationships between different sub-components, causing the loss of complementary information between multiple…

The diffusion transformer (DiT) architecture has attracted significant attention in image generation, achieving better fidelity, performance, and diversity. However, most existing DiT - based image generation methods focus on global - aware…

Advances in vision language models (VLMs) have enabled the simulation of general human behavior through their reasoning and problem solving capabilities. However, prior research has not investigated such simulation capabilities in the…

Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though…

Low-light image enhancement (LLIE) faces persistent challenges in balancing reconstruction fidelity with cross-scenario generalization. While existing methods predominantly focus on deterministic pixel-level mappings between paired…

We aim to address sparse-view reconstruction of a 3D scene by leveraging priors from large-scale vision models. While recent advancements such as 3D Gaussian Splatting (3DGS) have demonstrated remarkable successes in 3D reconstruction,…

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…

This paper presents a Progressively-connected Light Field network (ProLiF), for the novel view synthesis of complex forward-facing scenes. ProLiF encodes a 4D light field, which allows rendering a large batch of rays in one training step…

In recent years, learning-based underwater image enhancement (UIE) techniques have rapidly evolved. However, distribution shifts between high-quality enhanced outputs and natural images can hinder semantic cue extraction for downstream…

Due to the singularity of real-world paired datasets and the complexity of low-light environments, this leads to supervised methods lacking a degree of scene generalisation. Meanwhile, limited by poor lighting and content guidance, existing…

Existing state-of-the-art AI-Generated image detection methods mostly consider extracting low-level information from RGB images to help improve the generalization of AI-Generated image detection, such as noise patterns. However, these…

Image restoration and enhancement is a process of improving the image quality by removing degradations, such as noise, blur, and resolution degradation. Deep learning (DL) has recently been applied to image restoration and enhancement. Due…

People often imagine relevant scenes to aid in the writing process. In this work, we aim to utilize visual information for composition in the same manner as humans. We propose a method, LIVE, that makes pre-trained language models (PLMs)…

Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even editing steps, leading to significant improvements in image…

Vision-language pre-training (VLP) methods are blossoming recently, and its crucial goal is to jointly learn visual and textual features via a transformer-based architecture, demonstrating promising improvements on a variety of…

Most existing image compression approaches perform transform coding in the pixel space to reduce its spatial redundancy. However, they encounter difficulties in achieving both high-realism and high-fidelity at low bitrate, as the…

Aligning large VLMs with human preferences is a challenging task, as methods like RLHF and DPO often overfit to textual information or exacerbate hallucinations. Although augmenting negative image samples partially addresses these pitfalls,…

In this paper, we propose the generative patch prior (GPP) that defines a generative prior for compressive image recovery, based on patch-manifold models. Unlike learned, image-level priors that are restricted to the range space of a…