Improving the Rate-distortion Model of HEVC Intra by Integrating the Maximum Absolute Error

Jaskolka, Karina; Kaup, André

doi:10.1109/icassp.2019.8683418

Cited by 2 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, they used a hybrid approach combining the SSE distortion measurement with the structural similarity index (SSIM) to increase the subjective quality while still preserving the image fidelity. Another approach considers the maximum pixel error instead of the SSE which showed superior results for medical content [14]. Lastly, the authors in [15] proved that it is possible to decrease the decoding energy when adding an estimated decoding energy term to the RDO.…”

Section: Rate Distortion Optimization and Block Partitioning In Vvc A...mentioning

confidence: 99%

Video Coding for Machines with Feature-Based Rate-Distortion Optimization

Fischer

Brand

Herglotz

et al. 2020

2020 IEEE 22nd International Workshop on Multimedia Signal Processing (MMSP)

Self Cite

View full text Add to dashboard Cite

Common state-of-the-art video codecs are optimized to deliver a low bitrate by providing a certain quality for the final human observer, which is achieved by rate-distortion optimization (RDO). But, with the steady improvement of neural networks solving computer vision tasks, more and more multimedia data is not observed by humans anymore, but directly analyzed by neural networks. In this paper, we propose a standard-compliant feature-based RDO (FRDO) that is designed to increase the coding performance, when the decoded frame is analyzed by a neural network in a video coding for machine scenario. To that extent, we replace the pixel-based distortion metrics in conventional RDO of VTM-8.0 with distortion metrics calculated in the feature space created by the first layers of a neural network. Throughout several tests with the segmentation network Mask R-CNN and single images from the Cityscapes dataset, we compare the proposed FRDO and its hybrid version HFRDO with different distortion measures in the feature space against the conventional RDO. With HFRDO, up to 5.49 % bitrate can be saved compared to the VTM-8.0 implementation in terms of Bjøntegaard Delta Rate and using the weighted average precision as quality metric. Additionally, allowing the encoder to vary the quantization parameter results in coding gains for the proposed HFRDO of up 9.95 % compared to conventional VTM.

show abstract

Section: Rate Distortion Optimization and Block Partitioning In Vvc A...mentioning

confidence: 99%