Scope of validity of PSNR in image/video quality assessment
2008/06/19 by Q. Huynh-Thu, Quan Huynh‐Thu, M. Ghanbari · 2,855 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Artificial intelligence #Codec #Computer science #Computer vision #Data mining #Engineering #Image (mathematics) #Image and Video Quality Assessment #Image quality #Measure (data warehouse) #Metric (unit) #PEVQ #Peak signal-to-noise ratio #Quality (philosophy) #Scope (computer science) #Subjective video quality #Telecommunications #Video Coding and Compression Technologies #Video quality
paper · doi:10.1049/el:20080522
published in Electronics Letters 44(13), 800-801 (Institution of Engineering and Technology)
openalex publication_date 2008/06/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Abstract
Experimental data are presented that clearly demonstrate the scope of application of peak signal-to-noise ratio (PSNR) as a video quality metric. It is shown that as long as the video content and the codec type are not changed, PSNR is a valid quality measure. However, when the content is changed, correlation between subjective quality and PSNR is highly reduced. Hence PSNR cannot be a reliable method for assessing the video quality across different video contents.
Cited by
- Multi-level thresholding segmentation for pathological images: Optimal performance design of a new modified differential evolution
- SlerpFlow: Spherical Trajectory Correction for Rectified Flow Inversion
- A neural network with encoded visible edge prior for limited‐angle computed tomography reconstruction
- MR-Compare: A Mixed-Reality Framework for Spatially Grounded Visual Comparison of 3D Gaussian Splatting and Mesh Reconstructions with the Physical Environment
- SWITi: Quantifying and Reducing Tiling Artifacts with Sliding Window Inner Tiling
- From Rain Generation to Rain Removal
- ProEdit: Inversion-based Editing From Prompts Done Right
- A Novel Approach Towards Clustering Based Image Segmentation
- SplatBright: Generalizable Low-Light Scene Reconstruction from Sparse Views via Physically-Guided Gaussian Enhancement
- STORM: Search-Guided Generative World Models for Robotic Manipulation
- Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks
- MVGSR: Multi-View Consistent 3D Gaussian Super-Resolution via Epipolar Guidance
- End-to-End Learning-based Video Streaming Enhancement Pipeline: A Generative AI Approach
- Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprints
- DirectSwap: Mask-Free Cross-Identity Training and Benchmarking for Expression-Consistent Video Head Swapping
- Secure Audio Embedding in Images using Nature-Inspired Optimization
- Driving scene image Dehazing model based on multi-branch and multi-scale feature fusion
- LatentFM: A Latent Flow Matching Approach for Generative Medical Image Segmentation
- SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows
- Diffusion Model in Latent Space for Medical Image Segmentation Task
- Deep Joint Rain Detection and Removal from a Single Image
- Enhanced nonconvex low-rank approximation of tensor multi-modes for tensor completion
- Semantics and Content Matter: Towards Multi-Prior Hierarchical Mamba for Image Deraining
- Multi-modal and frequency-weighted tensor nuclear norm for hyperspectral image denoising
- ADRN: Attention-based Deep Residual Network for Hyperspectral Image Denoising
- FitVid: Overfitting in Pixel-Level Video Prediction
- Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
- Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning
- PreResQ-R1: Towards Fine-Grained Rank-and-Score Reinforcement Learning for Visual Quality Assessment via Preference-Response Disentangled Policy Optimization
- Multi-Task Learning Enhanced Single Image De-Raining
- Optimization of pulsed thermography inspection by partial least-squares regression
- 3DGBGS: 3D Granular Ball Gaussian Splatting for Compact Novel View Synthesis
- CGGAN: A Context Guided Generative Adversarial Network For Single Image Dehazing
- Unsupervised Single Image Deraining with Self-supervised Constraints
- Prioritization vs. congestion on platforms: evidence from Amazon's Twitch.tv
- InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry
- Shift-Net: Image Inpainting via Deep Feature Rearrangement
- Optical attenuation coefficient based optical coherence tomography angiography
- DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks
- Single Image Super Resolution based on a Modified U-net with Mixed Gradient Loss
- One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signal
- Residual Diffusion Bridge Model for Image Restoration
- DynaPose4D: High-Quality 4D Dynamic Content Generation via Pose Alignment Loss
- Frequency-Spatial Interaction Driven Network for Low-Light Image Enhancement
- Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery
- From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction
- Realistic Large-Scale Fine-Depth Dehazing Dataset from 3D Videos
- Rethinking Nighttime Image Deraining via Learnable Color Space Transformation
- A Model-driven Deep Neural Network for Single Image Rain Removal
- RoDyn: Taming Interactive Robot-Dynamic 2.5D World Model for Robotic Manipulation
- Defense against Unauthorized Distillation in Image Restoration via Feature Space Perturbation
- DeRainMamba: A Frequency-Aware State Space Model with Detail Enhancement for Image Deraining
- Joint Self-Attention and Scale-Aggregation for Self-Calibrated Deraining Network
- World-Env: Leveraging World Model as a Virtual Environment for VLA Post-Training
- Latent Representation Learning from 3D Brain MRI for Interpretable Prediction in Multiple Sclerosis
- VAMamba: An Efficient Visual Adaptive Mamba for Image Restoration
- FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
- ControlHair: Synergizing Physics Simulator and Video Diffusion for Controllable Dynamic Hair Rendering
- Compact Representation of Mipmapped SVBRDFs via Shared Gaussians
- S-Avatar: Diffusion-Guided Gaussian Head Avatars from a Single Image
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution
- GWM: Towards Scalable Gaussian World Models for Robotic Manipulation
- Enhanced artificial intelligence-based diagnosis using CBCT with internal denoising: Clinical validation for discrimination of fungal ball, sinusitis, and normal cases in the maxillary sinus
- SAMPO:Scale-wise Autoregression with Motion PrOmpt for generative world models
- Multi-Head Linear Attention Generative Adversarial Network for Thin Cloud Removal
- Every Camera Effect, Every Time, All at Once: 4D Gaussian Ray Tracing for Physics-based Camera Effect Data Generation
- Dense U-net for super-resolution with shuffle pooling layer
- VQualA 2025 Challenge on Visual Quality Comparison for Large Multimodal Models: Methods and Results
- Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining
- A Unified Low-level Foundation Model for Enhancing Pathology Image Quality
- UPGS: Unified Pose-aware Gaussian Splatting for Dynamic Scene Deblurring
- MangaDiT: Reference-Guided Line Art Colorization with Hierarchical Attention in Diffusion Transformers
- Exploring Palette based Color Guidance in Diffusion Models
- IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
- Follow-Your-Shape: Shape-Aware Image Editing via Trajectory-Guided Region Control
- CannyEdit: Selective Canny Control and Dual-Prompt Guidance for Training-Free Image Editing
- Mechanisms for Resilient Video Transmission
- Multi-mode Core Tensor Factorization based Low-Rankness and Its Applications to Tensor Completion
- GL-LCM: Global-Local Latent Consistency Models for Fast High-Resolution Bone Suppression in Chest X-Ray Images
- Cascade EF-GAN: Progressive Facial Expression Editing with Local Focuses
- Compressed Sensing MRI via a Multi-scale Dilated Residual Convolution Network
- Modeling optical imaging pipeline and learning contrastive-based representation for hybrid-corrupted image restoration
- Denoising of computed tomography using bilateral median based autoencoder network
- Think-Before-Draw: Decomposing Emotion Semantics & Fine-Grained Controllable Expressive Talking Head Generation
- Residual Squeeze-and-Excitation Network for Fast Image Deraining
- Backdoors in Conditional Diffusion: Threats to Responsible Synthetic Data Pipelines
- Flux-Sculptor: Text-Driven Rich-Attribute Portrait Editing through Decomposed Spatial Flow Control
- Improving precision of objective image/video quality metrics
- SurgVisAgent: Multimodal Agentic Model for Versatile Surgical Visual Enhancement
- When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach
- A Note on Efficiency of Downsampling and Color Transformation in Image Quality Assessment
- Tensor completion using enhanced multiple modes low-rank prior and total variation
- DBMovi-GS: Dynamic View Synthesis from Blurry Monocular Video via Sparse-Controlled Gaussian Splatting
- DerainCycleGAN: Rain Attentive CycleGAN for Single Image Deraining and Rainmaking
- Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction
- FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensembles
- Beyond Convolutions: A Novel Deep Learning Approach for Raw Seismic Data Ingestion
- Structural Residual Learning for Single Image Rain Removal
- VP-GO: a "light" action-conditioned visual prediction model
- ORV: 4D Occupancy-centric Robot Video Generation
- Does Haze Removal Help CNN-based Image Classification?
- Long-Context State-Space Video World Models
- SelfWAM: A Self-Grounded Unified World Action Model for Fast Robot Control
- OB3D: A New Dataset for Benchmarking Omnidirectional 3D Reconstruction Using Blender
- Resource Efficient LDPC Decoders for Multimedia Communication
- Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion Models
- Deep Learning-Driven Ultra-High-Definition Image Restoration: A Survey
- RLVR-World: Training World Models with Reinforcement Learning
- Remote Sensing Image Superresolution Using Deep Residual Channel Attention
- Degradation-Aware Feature Perturbation for All-in-One Image Restoration
- NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Results
- FlowDreamer: A RGB-D World Model with Flow-based Motion Representations for Robot Manipulation
- AnonymousNet: Natural Face De-Identification with Measurable Privacy
- GIQA: Generated Image Quality Assessment
- MoECa: Aligning Feature Reuse with Expert Decomposition in Diffusion Transformers
- Rain Removal and Illumination Enhancement Done in One Go
- DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
- PRISM-DP: Spatial Pose-based Observations for Diffusion-Policies via Segmentation, Mesh Generation, and Pose Tracking
- AnimateAnywhere: Rouse the Background in Human Image Animation
- Low-complexity 8-point DCT approximations based on integer functions
- A Machine Learning and Finite Element Framework for Inverse Elliptic PDEs via Dirichlet-to-Neumann Mapping
- ECGDeDRDNet: A deep learning-based method for Electrocardiogram noise removal using a double recurrent dense network
- Fragile Watermarking for Image Certification Using Deep Steganographic Embedding
- A Comparative Study of Various Deep Learning Techniques for Spatio-Temporal Super-Resolution Reconstruction of Forced Isotropic Turbulent Flows
- UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models
- A distance-field based automatic neuron tracing method. [europepmc]
- Brain MR image denoising for Rician noise using pre-smooth non-local means filter. [europepmc]
- Birdsong Denoising Using Wavelets. [europepmc]
- Application of Super-Resolution Convolutional Neural Network for Enhancing Image Resolution in Chest CT. [europepmc]
- Wavelet compression of off-axis digital holograms using real/imaginary and amplitude/phase parts. [europepmc]
- Attenuation of stripe artifacts in optical coherence tomography images through wavelet-FFT filtering. [europepmc]
- Optical Camera Communications for IoT-Rolling-Shutter Based MIMO Scheme with Grouped LED Array Transmitter. [europepmc]
- Performance of Vehicular Visible Light Communications under the Effects of Atmospheric Turbulence with Aperture Averaging. [europepmc]
- Stream-Based Visually Lossless Data Compression Applying Variable Bit-Length ADPCM Encoding. [europepmc]
- A Hybrid Preaching Optimization Algorithm Based on Kapur Entropy for Multilevel Thresholding Color Image Segmentation. [europepmc]
- ShapeEditor: A StyleGAN Encoder for Stable and High Fidelity Face Swapping. [europepmc]
- Adaptive Digital Hologram Binarization Method Based on Local Thresholding, Block Division and Error Diffusion. [europepmc]
- Impact of the suboptimal communication network environment on telerobotic surgery performance and surgeon fatigue. [europepmc]
- Inter-Slice Resolution Improvement Using Convolutional Neural Network with Orbital Bone Edge-Aware in Facial CT Images. [europepmc]
- Deep learning-based low-dose CT for adaptive radiotherapy of abdominal and pelvic tumors. [europepmc]
- Multi-threshold image segmentation for melanoma based on Kapur's entropy using enhanced ant colony optimization. [europepmc]
- AI-based radiodiagnosis using chest X-rays: A review. [europepmc]
- An efficient multilevel image thresholding method based on improved heap-based optimizer. [europepmc]
- Renal Pathology Images Segmentation Based on Improved Cuckoo Search with Diffusion Mechanism and Adaptive Beta-Hill Climbing. [europepmc]
- Face Image Segmentation Using Boosted Grey Wolf Optimizer. [europepmc]
- FEUSNet: Fourier Embedded U-Shaped Network for Image Denoising. [europepmc]
- Stripe noise removal in conductive atomic force microscopy. [europepmc]
- Unsupervised inter-domain transformation for virtually stained high-resolution mid-infrared photoacoustic microscopy using explainable deep learning. [europepmc]
- Similarity and quality metrics for MR image-to-image translation. [europepmc]
- Menstrual cycle inspired latent diffusion model for image augmentation in energy production. [europepmc]
Related