Yong Guo

Affiliations

South China University of Technology

papers

642

total citations

papers (20)

Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images

ICCV 2023arXiv

citations

Improving Robustness by Enhancing Weak Subnets

ECCV 2022arXiv

citations

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

NEURIPS 2025arXiv

citations

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

CVPR 2025arXiv

citations

Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis

ICCV 2025arXiv

citations

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement

NEURIPS 2025arXiv

citations

Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions

CVPR 2024arXiv

citations

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

NEURIPS 2025arXiv

citations

Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal

ICCV 2025arXiv

citations

Segment Any-Quality Images with Generative Latent Space Enhancement

CVPR 2025arXiv

citations

BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution

ICML 2025arXiv

citations

Temporal Action Detection Model Compression by Progressive Block Drop

CVPR 2025arXiv

citations

Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions

CVPR 2023

citations

CoDe: An Explicit Content Decoupling Framework for Image Restoration

CVPR 2024

citations

Restabilizing Diffusion Models with Predictive Noise Fusion Strategy for Image Super-Resolution

AAAI 2025

citations

Yong Guo

Affiliations

papers (20)

Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution

MambaIRv2: Attentive State Space Restoration

Contrastive Neural Architecture Search With Neural Architecture Comparators

Robustifying Token Attention for Vision Transformers

Effective Diffusion Transformer Architecture for Image Super-Resolution

Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images

Improving Robustness by Enhancing Weak Subnets

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement

Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal

Segment Any-Quality Images with Generative Latent Space Enhancement

BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution

Temporal Action Detection Model Compression by Progressive Block Drop

Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions

CoDe: An Explicit Content Decoupling Framework for Image Restoration

Restabilizing Diffusion Models with Predictive Noise Fusion Strategy for Image Super-Resolution

papers (20)

Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution

MambaIRv2: Attentive State Space Restoration

Contrastive Neural Architecture Search With Neural Architecture Comparators

Robustifying Token Attention for Vision Transformers

Effective Diffusion Transformer Architecture for Image Super-Resolution

Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images

Improving Robustness by Enhancing Weak Subnets

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

PassionSR: Post-Training Quantization with Adaptive Scale in One-Step Diffusion based Image Super-Resolution

Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement

Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

Compression-Aware One-Step Diffusion Model for JPEG Artifact Removal

Segment Any-Quality Images with Generative Latent Space Enhancement

BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution

Temporal Action Detection Model Compression by Progressive Block Drop

Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions

CoDe: An Explicit Content Decoupling Framework for Image Restoration

Restabilizing Diffusion Models with Predictive Noise Fusion Strategy for Image Super-Resolution