Super-resolution of HEVC videos via convex optimization

Benoit Boyadjis (1, 2) , Beatrice Pesquet-Popescu (1, 2) , Frederic Dufaux (1, 2) , Cyril Bergeron

1 MM - Multimédia
2 TSI - Département Traitement du Signal et des Images

Super Resolution (SR) addresses the problem of image and video upscaling. Most of the best performing SR methods do not take into account any compression prior into the degradation model. Consequently, compression artifacts can be undesirably amplified during SR. In the present work, we propose a novel HEVC-dedicated approach for embedding SR results into a domain that closely fits the compressed observation. Our main contribution is the inclusion of HEVC syntax (block size, quantization parameters etc.) into the degradation model. A recent convex optimization approach is used to solve the associated minimization problem. Over a wide range of resolutions and bitrates, we show that our method improves the results obtained with state of the art SR.

Domains: Engineering Sciences [physics]; Signal and Image processing

Benoit Boyadjis, Beatrice Pesquet-Popescu, Frederic Dufaux, Cyril Bergeron. Super-resolution of HEVC videos via convex optimization. IEEE International Conference on Image Processing (ICIP’2016), Sep 2016, Phoenix, United States. ⟨hal-01433774⟩