@misc{HerglotzOchMeyeretal., author = {Herglotz, Christian and Och, Hannah and Meyer, Anna and Ramasubbu, Geetha and Eicherm{\"u}ller, Lena and Kr{\"a}nzler, Matthias and Brand, Fabian and Fischer, Kristian and Nguyen, Dat Thanh and Regensky, Andy and Kaup, Andr{\´e}}, title = {The Bj{\o}ntegaard Bible Why Your Way of Comparing Video Codecs May Be Wrong}, series = {IEEE Transactions on Image Processing}, journal = {IEEE Transactions on Image Processing}, number = {Volume 33}, issn = {1057-7149}, doi = {10.1109/TIP.2023.3346695}, pages = {987 -- 1001}, abstract = {In this paper, we provide an in-depth assessment on the Bj{\o}ntegaard Delta. We construct a large data set of video compression performance comparisons using a diverse set of metrics including PSNR, VMAF, bitrate, and processing energies. These metrics are evaluated for visual data types such as classic perspective video, 360° video, point clouds, and screen content. As compression technology, we consider multiple hybrid video codecs as well as state-of-the-art neural network based compression methods. Using additional supporting points in-between standard points defined by parameters such as the quantization parameter, we assess the interpolation error of the Bj{\o}ntegaard-Delta (BD) calculus and its impact on the final BD value. From the analysis, we find that the BD calculus is most accurate in the standard application of rate-distortion comparisons with mean errors below 0.5 percentage points. For other applications and special cases, e.g., VMAF quality, energy considerations, or inter-codec comparisons, the errors are higher (up to 5 percentage points), but can be halved by using a higher number of supporting points. We finally come up with recommendations on how to use the BD calculus such that the validity of the resulting BD-values is maximized. Main recommendations are as follows: First, relative curve differences should be plotted and analyzed. Second, the logarithmic domain should be used for saturating metrics such as SSIM and VMAF. Third, BD values below a certain threshold indicated by the subset error should not be used to draw recommendations. Fourth, using two supporting points is sufficient to obtain rough performance estimates.}, language = {en} } @misc{EichermuellerChaudhariKatsavounidisetal., author = {Eicherm{\"u}ller, Lena and Chaudhari, Gaurang and Katsavounidis, Ioannis and Lei, Zhijun and Tmar, Hassene and Herglotz, Christian and Kaup, Andr{\´e}}, title = {Encoding Time and Energy Model for SVT-AV1 Based on Video Complexity}, series = {ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, journal = {ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, publisher = {IEEE}, isbn = {979-8-3503-4485-1}, issn = {2379-190X}, doi = {10.1109/ICASSP48485.2024.10446602}, pages = {3370 -- 3374}, abstract = {The share of online video traffic in global carbon dioxide emissions is growing steadily. To comply with the demand for video media, dedicated compression techniques are continuously optimized, but at the expense of increasingly higher computational demands and thus rising energy consumption at the video encoder side. In order to find the best trade-off between compression and energy consumption, modeling encoding energy for a wide range of encoding parameters is crucial. We propose an encoding time and energy model for SVT-AV1 based on empirical relations between the encoding time and video parameters as well as encoder configurations. Furthermore, we model the influence of video content by established content descriptors such as spatial and temporal information. We then use the predicted encoding time to estimate the required energy demand and achieve a prediction error of 19.6\% for encoding time and 20.9\% for encoding energy.}, language = {en} } @misc{EichermuellerChaudhariKatsavounidisetal., author = {Eicherm{\"u}ller, Lena and Chaudhari, Gaurang and Katsavounidis, Ioannis and Lei, Zhijun and Tmar, Hassene and Herglotz, Christian and Kaup, Andr{\´e}}, title = {SVT-AV1 Encoding Bitrate Estimation Using Motion Search Information}, series = {32nd European Signal Processing Conference (EUSIPCO)}, journal = {32nd European Signal Processing Conference (EUSIPCO)}, publisher = {IEEE}, isbn = {978-9-4645-9361-7}, issn = {2076-1465}, pages = {937 -- 941}, abstract = {Enabling high compression efficiency while keeping encoding energy consumption at a low level, requires prioritization of which videos need more sophisticated encoding techniques. However, the effects vary highly based on the content, and information on how good a video can be compressed is required. This can be measured by estimating the encoded bitstream size prior to encoding. We identified the errors between estimated motion vectors from Motion Search, an algorithm that predicts temporal changes in videos, correlates well to the encoded bitstream size. Combining Motion Search with Random Forests, the encoding bitrate can be estimated with a Pearson correlation of above 0.96.}, language = {en} } @misc{EichermuellerChaudhariKatsavounidisetal., author = {Eicherm{\"u}ller, Lena and Chaudhari, Gaurang and Katsavounidis, Ioannis and Lei, Zhijun and Tmar, Hassene and Herglotz, Christian and Kaup, Andre}, title = {Encoding Time and Energy Model for SVT-AV1 based on Video Complexity}, series = {arXiv - accepted for IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}, journal = {arXiv - accepted for IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)}, doi = {10.48550/arXiv.2401.16067}, pages = {5}, abstract = {The share of online video traffic in global carbon dioxide emissions is growing steadily. To comply with the demand for video media, dedicated compression techniques are continuously optimized, but at the expense of increasingly higher computational demands and thus rising energy consumption at the video encoder side. In order to find the best trade-off between compression and energy consumption, modeling encoding energy for a wide range of encoding parameters is crucial. We propose an encoding time and energy model for SVT-AV1 based on empirical relations between the encoding time and video parameters as well as encoder configurations. Furthermore, we model the influence of video content by established content descriptors such as spatial and temporal information. We then use the predicted encoding time to estimate the required energy demand and achieve a prediction error of 19.6 \% for encoding time and 20.9 \% for encoding energy.}, language = {en} }