Guangming Shi

papers

639

total citations

papers (19)

MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment

CVPR 2020arXiv

357

citations

Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging

CVPR 2021arXiv

169

citations

Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging

CVPR 2023arXiv

citations

EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation

CVPR 2021arXiv

citations

Triad: Empowering LMM-based Anomaly Detection with Expert-guided Region-of-Interest Tokenizer and Manufacturing Process

ICCV 2025

citations

Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events

AAAI 2024

citations

Unsupervised Curriculum Domain Adaptation for No-Reference Video Quality Assessment

ICCV 2021

citations

Feature Information Driven Position Gaussian Distribution Estimation for Tiny Object Detection

CVPR 2025

citations

Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring

CVPR 2023

citations

Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes

CVPR 2025

citations

Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion Deblurring

AAAI 2025

citations

Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens

CVPR 2024

citations

Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution

ECCV 2022

citations

Self-Feature Distillation with Uncertainty Modeling for Degraded Image Recognition

ECCV 2022

citations

Vector Quantization With Self-Attention for Quality-Independent Representation Learning

CVPR 2023

citations

Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention

ICCV 2023

citations

Guangming Shi

papers (19)

MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment

Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging

Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging

EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation

Inverse Weight-Balancing for Deep Long-Tailed Learning

BVT-IMA: Binary Vision Transformer with Information-Modified Attention

Parameterized Blur Kernel Prior Learning for Local Motion Deblurring

Triad: Empowering LMM-based Anomaly Detection with Expert-guided Region-of-Interest Tokenizer and Manufacturing Process

Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events

Unsupervised Curriculum Domain Adaptation for No-Reference Video Quality Assessment

Feature Information Driven Position Gaussian Distribution Estimation for Tiny Object Detection

Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring

Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes

Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion Deblurring

Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens

Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution

Self-Feature Distillation with Uncertainty Modeling for Degraded Image Recognition

Vector Quantization With Self-Attention for Quality-Independent Representation Learning

Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention

papers (19)

MetaIQA: Deep Meta-Learning for No-Reference Image Quality Assessment

Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging

Residual Degradation Learning Unfolding Framework With Mixing Priors Across Spectral and Spatial for Compressive Spectral Imaging

EffiScene: Efficient Per-Pixel Rigidity Inference for Unsupervised Joint Learning of Optical Flow, Depth, Camera Pose and Motion Segmentation

Inverse Weight-Balancing for Deep Long-Tailed Learning

BVT-IMA: Binary Vision Transformer with Information-Modified Attention

Parameterized Blur Kernel Prior Learning for Local Motion Deblurring

Triad: Empowering LMM-based Anomaly Detection with Expert-guided Region-of-Interest Tokenizer and Manufacturing Process

Motion Deblurring via Spatial-Temporal Collaboration of Frames and Events

Unsupervised Curriculum Domain Adaptation for No-Reference Video Quality Assessment

Feature Information Driven Position Gaussian Distribution Estimation for Tiny Object Detection

Self-Supervised Non-Uniform Kernel Estimation With Flow-Based Motion Prior for Blind Image Deblurring

Gain from Neighbors: Boosting Model Robustness in the Wild via Adversarial Perturbations Toward Neighboring Classes

Asymmetric Hierarchical Difference-aware Interaction Network for Event-guided Motion Deblurring

Segment Any Event Streams via Weighted Adaptation of Pivotal Tokens

Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution

Self-Feature Distillation with Uncertainty Modeling for Degraded Image Recognition

Vector Quantization With Self-Attention for Quality-Independent Representation Learning

Low-Light Image Enhancement with Multi-Stage Residue Quantization and Brightness-Aware Attention