Adversarial Distortion for Learned Video Compression
This addresses video compression quality for applications requiring efficient transmission, but it is incremental as it builds on existing learned neural approaches.
The paper tackles the problem of unpleasant reconstruction artifacts and blurred results in learned video compression at extremely low bit-rates by introducing an adversarial distortion objective, which reduces perceptual artifacts and reconstructs lost detail under high compression.
In this paper, we present a novel adversarial lossy video compression model. At extremely low bit-rates, standard video coding schemes suffer from unpleasant reconstruction artifacts such as blocking, ringing etc. Existing learned neural approaches to video compression have achieved reasonable success on reducing the bit-rate for efficient transmission and reduce the impact of artifacts to an extent. However, they still tend to produce blurred results under extreme compression. In this paper, we present a deep adversarial learned video compression model that minimizes an auxiliary adversarial distortion objective. We find this adversarial objective to correlate better with human perceptual quality judgement relative to traditional quality metrics such as MS-SSIM and PSNR. Our experiments using a state-of-the-art learned video compression system demonstrate a reduction of perceptual artifacts and reconstruction of detail lost especially under extremely high compression.