Combining Contrastive and Supervised Learning for Video Super-Resolution Detection

TL;DR

This paper introduces a novel video upscaling detection method combining contrastive and supervised learning, effectively identifying resolution enhancements in videos, including compressed ones, outperforming existing methods.

Contribution

The work presents a new learning-based framework for detecting upscaled videos that leverages contrastive and cross-entropy losses, with insights into data augmentation impacts.

Findings

Effective detection of upscaling in compressed videos

Outperforms state-of-the-art detection methods

Provides publicly available code and models

Abstract

Upscaled video detection is a helpful tool in multimedia forensics, but it is a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and deep-learning-based super-resolution, and they leave unique traces. In this work, we propose a new upscaled-resolution-detection method based on learning of visual representations using contrastive and cross-entropy losses. To explain how the method detects videos, we systematically review the major components of our framework - in particular, we show that most data-augmentation approaches hinder the learning of the method. Through extensive experiments on various datasets, we demonstrate that our method effectively detects upscaling even in compressed videos and outperforms the state-of-the-art alternatives. The code and models are publicly available at https://github.com/msu-video-group/SRDM