1.2k citations · 1.8k across the 51 of their papers we have counts for
52 papers
Position: Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered
Jinfan Hu, Fanghua Yu, Zhiyuan You +5
This position paper argues that the evaluation of modern visual processing systems should no longer be driven primarily by single-metric image quality assessment benchmarks, partic…
How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices
Xiang Yin, Jinfan Hu, Zhiyuan You +4
Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with previous methods? To answer…
Accelerating Masked Image Generation by Learning Controlled Latent Dynamics
Kaiwen Zhu, Quansheng Zeng, Yuandong Pu +9
Masked Image Generation Models (MIGMs) have achieved great success, yet their efficiency is hampered by the multiple steps of bi-directional attention. In fact, there exists notabl…
PhotoFramer: Multi-modal Image Composition Instruction
Zhiyuan You, Ke Wang, He Zhang +5
Composition matters during the photo-taking process, yet many casual users struggle to frame well-composed images. To provide composition guidance, we introduce PhotoFramer, a mult…
Harnessing Diffusion-Yielded Score Priors for Image Restoration
Xinqi Lin, Fanghua Yu, Jinfan Hu +5
Deep image restoration models aim to learn a mapping from degraded image space to natural image space. However, they face several critical challenges: removing degradation, generat…
UniCon: Unidirectional Information Flow for Effective Control of Large-Scale Diffusion Models
Fanghua Yu, Jinjin Gu, Jinfan Hu +2
We introduce UniCon, a novel architecture designed to enhance control and efficiency in training adapters for large-scale diffusion models. Unlike existing methods that rely on bid…
Revisiting the Generalization Problem of Low-level Vision Models Through the Lens of Image Deraining
Jinfan Hu, Zhiyuan You, Jinjin Gu +3
Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism of this failure, using im…
Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution
Zhiyuan You, Xin Cai, Jinjin Gu +2
With the rapid advancement of Multi-modal Large Language Models (MLLMs), MLLM-based Image Quality Assessment (IQA) methods have shown promising performance in linguistic quality de…
An Intelligent Agentic System for Complex Image Restoration Problems
Kaiwen Zhu, Jinjin Gu, Zhiyuan You +2
Real-world image restoration (IR) is inherently complex and often requires combining multiple specialized models to address diverse degradations. Inspired by human problem-solving,…
A Preliminary Exploration Towards General Image Restoration
Xiangtao Kong, Jinjin Gu, Yihao Liu +4
Despite the tremendous success of deep models in various individual image restoration tasks, there are at least two major technical challenges preventing these works from being app…
Interpreting Low-level Vision Models with Causal Effect Maps
Jinfan Hu, Jinjin Gu, Shiyao Yu +5
Deep neural networks have significantly improved the performance of low-level vision tasks but also increased the difficulty of interpretability. A deep understanding of deep model…
LM4LV: A Frozen Large Language Model for Low-level Vision Tasks
Boyang Zheng, Jinjin Gu, Shijun Li +1
The success of large language models (LLMs) has fostered a new research trend of multi-modality large language models (MLLMs), which changes the paradigm of various fields in compu…
Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset
Zhiyuan You, Jinjin Gu, Xin Cai +4
With the rapid advancement of Vision Language Models (VLMs), VLM-based Image Quality Assessment (IQA) seeks to describe image quality linguistically to align with human expression…
Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild
Fanghua Yu, Jinjin Gu, Zheyuan Li +6
We introduce SUPIR (Scaling-UP Image Restoration), a groundbreaking image restoration method that harnesses generative prior and the power of model scaling up. Leveraging multi-mod…
Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models
Zhiyuan You, Zheyuan Li, Jinjin Gu +3
We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based methods. DepictQA allows for detailed, language-based, hum…
Dual Aggregation Transformer for Image Super-Resolution
Zheng Chen, Yulun Zhang, Jinjin Gu +3
Transformer has recently gained considerable popularity in low-level vision tasks, including image super-resolution (SR). These networks utilize self-attention along different dime…
The 2023 Development of Room-Temperature Ambient-Pressure Superconductor: Vision and Future Trend of Power Systems
Yi Yang, Chenxi Zhang, Xinlei Wang +3
Room-Temperature Ambient-Pressure Superconductor (RTAPS) can achieve superconducting properties at room temperature and normal atmospheric pressure, eliminating the power system's…
Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution
Ruofan Zhang, Jinjin Gu, Haoyu Chen +3
Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate…
Networks are Slacking Off: Understanding Generalization Problem in Image Deraining
Jinjin Gu, Xianzheng Ma, Xiangtao Kong +2
Deep deraining networks consistently encounter substantial generalization issues when deployed in real-world applications, although they are successful in laboratory benchmarks. A…
Hierarchical Integration Diffusion Model for Realistic Image Deblurring
Zheng Chen, Yulun Zhang, Ding Liu +4
Diffusion models (DMs) have recently been introduced in image deblurring and exhibited promising performance, particularly in terms of details reconstruction. However, the diffusio…
Masked Image Training for Generalizable Deep Image Denoising
Haoyu Chen, Jinjin Gu, Yihao Liu +5
When capturing and storing images, devices inevitably introduce noise. Reducing this noise is a critical task called image denoising. Deep learning has become the de facto method f…
Xformer: Hybrid X-Shaped Transformer for Image Denoising
Jiale Zhang, Yulun Zhang, Jinjin Gu +3
In this paper, we present a hybrid X-shaped vision Transformer, named Xformer, which performs notably on image denoising tasks. We explore strengthening the global representation o…
Recursive Generalization Transformer for Image Super-Resolution
Zheng Chen, Yulun Zhang, Jinjin Gu +2
Transformer architectures have exhibited remarkable performance in image super-resolution (SR). Since the quadratic computational complexity of the self-attention (SA) in Transform…
Mitigating Artifacts in Real-World Video Super-Resolution Models
Liangbin Xie, Xintao Wang, Shuwei Shi +3
The recurrent structure is a prevalent framework for the task of video super-resolution, which models the temporal dependency between frames via hidden states. When applied to real…