Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Deyu MengSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works37 from public data
- Exploiting Diffusion Prior for Real-World Image Super-Resolution715
A novel approach to leverage prior knowledge encapsulated in pre-trained text-to-image diffusion models for blind super-resolution by employing the time-aware encoder can achieve promising restoration results without altering the pre-trained synthesis model, thereby preserving the generative prior and minimizing training cost.
- Dual Adversarial Network: Toward Real-World Noise Removal and Noise Generation265
A novel unified framework to simultaneously deal with the noise removal and noise generation tasks, instead of only inferring the posteriori distribution of the latent clean image conditioned on the observed noisy image in traditional MAP framework, which implicitly contains all the information between the noisy and clean images.
- 209
- DifFace: Blind Face Restoration With Diffused Error Contraction171
This work proposes a novel method named DifFace that is capable of coping with unseen and complex degradations more gracefully without complicated loss designs and can contract the error of the restoration backbone and thus makes this method more robust to unknown degradations.
- Efficient Diffusion Model for Image Restoration by Residual Shifting130
This study proposes a novel and efficient diffusion model for IR that significantly reduces the required number of diffusion steps, and establishes a Markov chain that facilitates the transitions between the high-quality and low-quality images by shifting their residuals, substantially improving the transition efficiency.
- 98
- Semi-Supervised Video Deraining with Dynamical Rain Generator95
A new semi-supervised video deraining method, in which a dynamical rain generator is employed to fit the rain layer for the sake of better depicting its intrinsic characteristics, and a Monte Carlo-based EM algorithm is designed to learn the model.
- Unsupervised hyperspectral pansharpening via low-rank diffusion model89
This work proposes a low-rank diffusion model for hyperspectral pansharpening by simultaneously leveraging the power of the pre-trained deep diffusion model and better generalization ability of Bayesian methods.
- Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel87
A model-based blind SISR method under the probabilistic framework is proposed, which elaborately models image degradation from the perspectives of noise and blur kernel, and a theoretically grounded Monte Carlo EM algorithm is specifically designed.
- 83
- Degradation-Guided One-Step Image Super-Resolution with Diffusion Priors78
This work introduced a novel one-step SR model, which significantly addresses the efficiency issue of diffusion-based SR methods and tailor a novel training pipeline by introducing an online negative sample generation strategy.
- SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training51
This work proposes a one-step diffusion-based VR model, termed as SeedVR2, which performs adversarial VR training against real data, and introduces several enhancements to both model architecture and training procedures to handle the challenging high-resolution VR within a single step.
- 46
- Deep Variational Network Toward Blind Image Restoration36
A general Bayesian generative model is constructed for the blind IR, which explicitly depicts the degradation process and a variational inference algorithm is designed where all the expected posteriori distributions are parameterized as deep neural networks to increase their model capability.
- 31
- A deep variational Bayesian framework for blind image deblurring24
A deep variational Bayesian framework for blind image deblurring is presented that can not only achieve a promising performance with relatively simple networks, but also enhance the performance of existing DNNs fordeblurring.
- MOWA: Multiple-in-One Image Warping Model19
This work proposes a Multiple-in-One image WArping model (named MOWA), the first work that solves multiple practical warping tasks in one single model and introduces a lightweight point-based classifier that predicts the task type and serves as prompts to modulate the feature maps for more accurate estimation.
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration17
This paper shows that it is possible to perform domain adaptation via the noise space using diffusion models and derives a meaningful diffusion loss that guides the restoration model in progressively aligning both restored synthetic and real-world outputs with a target clean distribution.
- Hyperspectral Image Restoration under Complex Multi-Band Noises16
This study elaborately constructs a new HSI restoration technique, aimed at more faithfully and comprehensively taking such noise characteristics into account, through a two-level hierarchical Dirichlet process (HDP) to model the HSI noise structure.
- MIPI 2024 Challenge on Few-shot RAW Image Denoising: Methods and Results15
The developed solutions in this challenge achieved state-of-the-art performance on Few-shot RAW Image Denoising and were summarized and reviewed in this paper.
- 15
- Semi-supervised learning through adaptive Laplacian graph trimming14
This study attempts to propose a method, called adaptive Laplacian graph trimming (ALGT), to make an automatic tuning to cut improper inter-clusters shortcut edges while enhance the connection between intra-cluster samples, so as to adaptively fit a proper LWR from data.
- MIPI 2024 Challenge on Demosaic for Hybridevs Camera: Methods and Results9
A total of 110 participants from both industrial and academic backgrounds contributed many valuable solutions to address the difficulty of the restoration of HybridEVS’s raw data, thus raising the reconstructed performance to a new height.
- Variational Image Restoration Network8
A unified generative model for the image restoration, which elaborately configures the degradation process from the latent clean image to the observed corrupted one, and designed a variational inference algorithm to learn all parameters involved in the proposed model with explicit form of objective loss.
- 6
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.