Parallel Rate Distortion Optimized Quantization for 4K Real-time GPU-based HEVC Encoder

We proposed a highly parallel rate distortion optimized quantization (RDOQ) for 4K real-time GPU-based HEVC encoder. RDOQ optimizes a quantized value in the view of a tradeoff relationship between picture quality and compression efficiency. While it brings better compression efficiency for HEVC, it is difficult to process on GPU. This is because two parts which compose RDOQ; the cost calculation and the optimization, are sequential. The proposed method parallelizes both of parts and accelerates RDOQ on GPU. For the cost calculation, the proposed method uses the history data of previous frame. Furthermore, to parallelize the optimization part, the proposed method applies bi-directional parallel scan which can be processed on GPU. Experimental results show that the proposed method improved 26.43 % of BD-rate compared with the conventional GPU-based encoder without RDOQ which enables 4K/60FPS real-time encoding. Furthermore, the proposed method is 5x faster than x265 which is the most practical CPU-based encoder under similar conditions of BD-rate.