19 citations · 67 across the 25 of their papers we have counts for
25 papers
GEAR: Guided End-to-End AutoRegression for Image Synthesis
Bin Lin, Zheyuan Liu, Chenguo Lin +8
Visual generative models are typically trained in two stages. A tokenizer is first trained for reconstruction and then frozen, after which a generator is trained on its discrete in…
SegDINO: Introducing Multi-Scale Structure into DINO for Efficient Medical Image Segmentation
Sicheng Yang, Hongqiu Wang, Zhaohu Xing +5
Self-supervised DINO models provide strong transferable visual representations, yet applying them directly to image segmentation remains challenging. Existing approaches commonly r…
GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
Sixiang Chen, Zhaohu Xing, Tian Ye +7
Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with ext…
Latent Action Control for Reasoning-Guided Unified Image Generation
Fuxiang Zhai, Sixiang Chen, Yingjin Li +4
Unified multimodal models can encode visual understanding and image generation within a shared backbone, yet understanding does not automatically translate into control: models may…
LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
Song Fei, Tian Ye, Sixiang Chen +3
Generative real-world image super-resolution (Real-ISR) can synthesize visually convincing details from severely degraded low-resolution (LR) inputs, yet its stochastic sampling ma…
An Empirical Study of GPT-4o Image Generation Capabilities
Sixiang Chen, Jinbin Bai, Zhuoran Zhao +16
The landscape of image generation has rapidly evolved, from early GAN-based approaches to diffusion models and, most recently, to unified generative architectures that seek to brid…
Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors
Yunlong Lin, Zhenqi Fu, Kairun Wen +7
Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments. Recent advanced LIE techniques are using deep ne…
Teaching Tailored to Talent: Adverse Weather Restoration via Prompt Pool and Depth-Anything Constraint
Sixiang Chen, Tian Ye, Kai Zhang +3
Recent advancements in adverse weather restoration have shown potential, yet the unpredictable and varied combinations of weather degradations in the real world pose significant ch…
Cross-conditioned Diffusion Model for Medical Image to Image Translation
Zhaohu Xing, Sicheng Yang, Sixiang Chen +4
Multi-modal magnetic resonance imaging (MRI) provides rich, complementary information for analyzing diseases. However, the practical challenges of acquiring multiple MRI modalities…
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
Haoyu Chen, Wenbo Li, Jinjin Gu +7
Natural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual…
AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
Yunlong Lin, Tian Ye, Sixiang Chen +6
Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limit…
NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results
Xiaoning Liu, Zongwei Wu, Ao Li +109
This paper reviews the NTIRE 2024 low light image enhancement challenge, highlighting the proposed solutions and results. The aim of this challenge is to discover an effective netw…
VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook
Wenbin Zou, Hongxia Gao, Tian Ye +5
Night photography often struggles with challenges like low light and blurring, stemming from dark environments and prolonged exposures. Current methods either disregard priors and…
Sparse Sampling Transformer with Uncertainty-Driven Ranking for Unified Removal of Raindrops and Rain Streaks
Sixiang Chen, Tian Ye, Jinbin Bai +3
In the real world, image degradations caused by rain often exhibit a combination of rain streaks and raindrops, thereby increasing the challenges of recovering the underlying clean…
Five A Network: You Only Need 9K Parameters for Underwater Image Enhancement
Jingxia Jiang, Tian Ye, Jinbin Bai +5
A lightweight underwater image enhancement network is of great significance for resource-constrained platforms, but balancing model size, computational efficiency, and enhancement…
NightHazeFormer: Single Nighttime Haze Removal Using Prior Query Transformer
Yun Liu, Zhongsheng Yan, Sixiang Chen +3
Nighttime image dehazing is a challenging task due to the presence of multiple types of adverse degrading effects including glow, haze, blurry, noise, color distortion, and so on.…
DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenes
Sixiang Chen, Tian Ye, Jun Shi +4
Varicolored haze caused by chromatic casts poses haze removal and depth estimation challenges. Recent learning-based depth estimation methods are mainly targeted at dehazing first…
RSFDM-Net: Real-time Spatial and Frequency Domains Modulation Network for Underwater Image Enhancement
Jingxia Jiang, Jinbin Bai, Yun Liu +4
Underwater images typically experience mixed degradations of brightness and structure caused by the absorption and scattering of light by suspended particles. To address this issue…
Dual-former: Hybrid Self-attention Transformer for Efficient Image Restoration
Sixiang Chen, Tian Ye, Yun Liu +1
Recently, image restoration transformers have achieved comparable performance with previous state-of-the-art CNNs. However, how to efficiently leverage such architectures remains a…
SnowFormer: Context Interaction Transformer with Scale-awareness for Single Image Desnowing
Sixiang Chen, Tian Ye, Yun Liu +1
Due to various and complicated snow degradations, single image desnowing is a challenging image restoration task. As prior arts can not handle it ideally, we propose a novel transf…
Towards Real-time High-Definition Image Snow Removal: Efficient Pyramid Network with Asymmetrical Encoder-decoder Architecture
Tian Ye, Sixiang Chen, Yun Liu +2
In winter scenes, the degradation of images taken under snow can be pretty complex, where the spatial distribution of snowy degradation is varied from image to image. Recent method…
MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing
Sixiang Chen, Tian Ye, Yun Liu +4
Snow removal causes challenges due to its characteristic of complex degradations. To this end, targeted treatment of multi-scale snow degradations is critical for the network to le…
Underwater Light Field Retention : Neural Rendering for Underwater Imaging
Tian Ye, Sixiang Chen, Yun Liu +3
Underwater Image Rendering aims to generate a true-tolife underwater image from a given clean one, which could be applied to various practical applications such as underwater image…
Towards Efficient Single Image Dehazing and Desnowing
Tian Ye, Sixiang Chen, Yun Liu +2
Removing adverse weather conditions like rain, fog, and snow from images is a challenging problem. Although the current recovery algorithms targeting a specific condition have made…