UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling

2026-04-13

AI Summary

This work addresses the challenge of ultra-high-definition (UHD) video denoising, which demands effective suppression of complex spatiotemporal degradations while preserving fine textures and color fidelity, all under the constraint of efficient full-resolution 4K processing. The authors propose UHD-GPGNet, the first method to explicitly integrate Gaussian processes (GPs) into UHD video denoising. It leverages sparse GP posteriors to model local degradation responses and their uncertainties, guiding adaptive temporal fusion. A structure-color collaborative reconstruction head is introduced to decouple the restoration of luminance, chrominance, and high-frequency components, further enhanced by a heteroscedastic loss for improved fidelity and generalization. Evaluated on UVG and RealisVideo-4K benchmarks, the method achieves state-of-the-art performance with fewer parameters, enables real-time 4K inference—significantly faster than existing approaches—and demonstrates strong generalization on real-world mobile videos, notably boosting downstream object detection accuracy.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Non-convex Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Ultra-high-definition (UHD) video denoising requires simultaneously suppressing complex spatio-temporal degradations, preserving fine textures and chromatic stability, and maintaining efficient full-resolution 4K deployment. In this paper, we propose UHD-GPGNet, a Gaussian-process-guided local spatio-temporal denoising framework that addresses these requirements jointly. Rather than relying on implicit feature learning alone, the method estimates sparse GP posterior statistics over compact spatio-temporal descriptors to explicitly characterize local degradation response and uncertainty, which then guide adaptive temporal-detail fusion. A structure-color collaborative reconstruction head decouples luminance, chroma, and high-frequency correction, while a heteroscedastic objective and overlap-tiled inference further stabilize optimization and enable memory-bounded 4K deployment. Experiments on UVG and RealisVideo-4K show that UHD-GPGNet achieves competitive restoration fidelity with substantially fewer parameters than existing methods, enables real-time full-resolution 4K inference with significant speedup over the closest quality competitor, and maintains robust performance across a multi-level mixed-degradation schedule.A real-world study on phone-captured 4K video further confirms that the model, trained entirely on synthetic degradation, generalizes to unseen real sensor noise and improves downstream object detection under challenging conditions.

Problem

• UHD video denoising
• spatio-temporal degradation
• texture preservation
• chromatic stability
• 4K deployment

Innovation

• Gaussian Process
• Spatio-Temporal Modeling
• UHD Video Denoising
• Adaptive Temporal Fusion
• Heteroscedastic Learning