A metric for Perceptual Image-Error Assessment through Pairwise Preference (PieAPP at CVPR 2018).
[ECCV 2024] Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
[INTERSPEECH 2026] This is the official implementation for εar-VAE model including inference and evaluation parts, more details coming soon...
[ Official ] - PIPAL Dataset and Training Codebase. ECCV-2020, NTIRE-21/22.
Learning-based Just-noticeable-quantization-distortion Model for perceptual video coding
Code for "Adversarial and Perceptual Refinement Compressed Sensing MRI Reconstruction"
Official code (Pytorch) for paper Perception-Enhanced Single Image Super-Resolution via Relativistic Generative Networks
Supplementary material for the paper "BL-JUNIPER: A CNN Assisted Framework for Perceptual Video Coding Leveraging Block Level JND", IEEE TMM 2022
Full-Reference Image Quality Assessment models based on ensemble of gradient boosting
Supplementary material for the paper "Lightweight Multitask Learning for Robust JND Prediction using Latent Space and Reconstructed Frames", IEEE TCSVT, 2024.
VMAFx: perceptual video quality assessment (VMAF), GPU-accelerated and SIMD-tuned. CUDA, SYCL, HIP and Metal backends checked against the CPU scores, AVX2/AVX-512/NEON, tiny-AI models, an MCP server, Kubernetes/Helm deployment. Fork of Netflix/vmaf; fork code EUPL-1.2, Netflix code BSD-2-Clause-Patent.
Supplementary material for the paper "PERCEPTUAL LEARNED IMAGE COMPRESSION VIA END-TO-END JND-BASED OPTIMIZATION", IEEE ICIP 2024
A tagged catalog of perceptual quality assessment: image quality, video quality, UGC and HDR. Methods and subjective datasets in one place, generated from CSV.
Supplementary material for the paper "MTJND: MULTI-TASK DEEP LEARNING FRAMEWORK FOR IMPROVED JND PREDICTION", IEEE ICIP 2023
Perceptual video compression under explicit quality and size constraints, with VMAF-guided search and independent holdout verification.
Full-reference objective quality index for reconstructed background images.
Fotos JPEG más livianas que se ven exactamente igual — app para macOS con compresión perceptual (Rust + Tauri). Lighter JPEGs that look the same.
A Java port of the perceptualdiff image comparison (pdiff.sourceforge.net)
Perceptual JND model for video coding — prune sub-threshold errors for 20-30% bitrate savings (Go + SIMD)
To associate your repository with the perceptual-quality topic, visit your repo's landing page and select "manage topics."