Abstract | ||
---|---|---|
Rate-Distortion Optimized Quantization (RDOQ) has played an important role in the coding performance of recent video compression standards such as H.264/AVC, H.265/HEVC, VP9 and AV1. This scheme yields significant reductions in bit-rate at the expense of relatively small increases in distortion. Typically, RDOQ algorithms are prohibitively expensive to implement on real-time hardware encoders due to their sequential nature and their need to frequently obtain entropy coding costs. This work addresses this limitation using a neural network-based approach, which learns to trade-off rate and distortion during offline supervised training. As these networks are based solely on standard arithmetic operations that can be executed on existing neural network hardware, no additional area-on-chip needs to be reserved for dedicated RDOQ circuitry. We train two classes of neural networks, a fully-convolutional network and an auto-regressive network, and evaluate each as a post-quantization step designed to refine cheap quantization schemes such as scalar quantization (SQ). Both network architectures are designed to have a low computational overhead. After training they are integrated into the HM 16.20 implementation of HEVC, and their video coding performance is evaluated on a subset of the H.266/VVC SDR common test sequences. Comparisons are made to RDOQ and SQ implementations in HM16.20. Our method achieves 1.64% BD-rate savings on luminosity compared to the HM SQ anchor, and on average reaches 45% of the performance of the iterative HM RDOQ algorithm. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/MMSP48831.2020.9287135 | 2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP) |
Keywords | DocType | ISSN |
deep learning,video compression standards,VP9,AV1,RDOQ algorithms,sequential nature,entropy coding costs,neural network-based approach,standard arithmetic operations,dedicated RDOQ circuitry,neural networks,fully-convolutional network,auto-regressive network,post-quantization step,scalar quantization,network architectures,video coding,SQ implementations,BD-rate savings,iterative HM RDOQ algorithm,parallelized rate-distortion optimized quantization,H.264/AVC,H.265/HEVC,real-time hardware encoders | Conference | 2163-3517 |
ISBN | Citations | PageRank |
978-1-7281-9323-6 | 0 | 0.34 |
References | Authors | |
8 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dana Kianfar | 1 | 0 | 0.34 |
Auke Wiggers | 2 | 0 | 0.34 |
Amir Said | 3 | 0 | 0.34 |
Pourreza Reza | 4 | 0 | 0.68 |
Taco Cohen | 5 | 228 | 17.82 |