Abstract
Video coding that pursues the highest compression efficiency is the art of computing for rate-distortion optimization. The optimization has been approached in different ways, exemplified by two typical frameworks: block-based hybrid video coding and end-to-end learned video coding. The block-based hybrid framework encompasses more and more coding modes that are available at the decoder side; an encoder tries to search for the optimal coding mode for each block to be coded. This is an online, discrete, search-based optimization strategy. The end-to-end learned framework embraces more and more sophisticated neural networks; the network parameters are learned from a collection of videos, typically using gradient descent-based methods. This is an offline, continuous, numerical optimization strategy. Having analyzed these two strategies, both conceptually and with concrete schemes, this paper suggests investigating hybrid-optimization video coding, that is to combine online and offline, discrete and continuous, search-based and numerical optimization. For instance, we propose a hybrid-optimization video coding scheme, where the decoder consists of trained neural networks and supports several coding modes, and the encoder adopts both numerical and search-based algorithms for the online optimization. Our scheme achieves promising compression efficiency on par with H.265/HM for the random-access configuration.
- [1] . 2017. Soft-to-hard vector quantization for end-to-end learning compressible representations. In NIPS, Vol. 30. 1141–1151.Google Scholar
- [2] . 2020. Scale-space flow for end-to-end optimized video compression. In CVPR. 8503–8512.Google ScholarCross Ref
- [3] . 2020. Universally quantized neural compression. In NeurIPS, Vol. 33. 12367–12376.Google Scholar
- [4] . 1974. Discrete cosine transform. IEEE Trans. Comput. C-23, 1 (1974), 90–93.Google ScholarDigital Library
- [5] . 2010. Bi-directional optical flow for improving motion compensation. In PCS. IEEE, 422–425.Google ScholarCross Ref
- [6] . 2016. End-to-end optimized image compression. arXiv preprint arXiv:1611.01704 (2016).Google Scholar
- [7] . 2018. Variational image compression with a scale hyperprior. arXiv preprint arXiv:1802.01436 (2018).Google Scholar
- [8] . 2001. Calculation of Average PSNR Differences between RD-Curves.
Technical Report VCEG-M33. VCEG.Google Scholar - [9] . 2011. Common Test Conditions and Software Reference Configurations.
Technical Report JCTVC-F900. JCT-VC.Google Scholar - [10] . 2021. Rate-distortion optimized learning-based image compression using an adaptive hierachical autoencoder with conditional hyperprior. In CVPR Workshops. 1885–1889.Google ScholarCross Ref
- [11] . 2021. Developments in international video coding standardization after AVC, with an overview of versatile video coding (VVC). Proc. IEEE 109, 9 (2021), 1463–1493.Google ScholarCross Ref
- [12] . 2021. Overview of the versatile video coding (VVC) standard and its applications. IEEE Transactions on Circuits and Systems for Video Technology 31, 10 (2021), 3736–3764.Google ScholarCross Ref
- [13] . 2018. Deep image compression with iterative non-uniform quantization. In ICIP. IEEE, 451–455.Google ScholarCross Ref
- [14] . 2019. Content adaptive optimization for neural image compression. In CVPR Workshops. 1–5.Google Scholar
- [15] . 2023. B-CANF: Adaptive B-frame coding with conditional augmented normalizing flows. IEEE Transactions on Circuits and Systems for Video Technology (2023).
DOI: Google ScholarCross Ref - [16] . 2000. Motion estimation using a one-dimensional gradient descent search. IEEE Transactions on Circuits and Systems for Video Technology 10, 4 (2000), 608–616.Google ScholarDigital Library
- [17] . 2021. End-to-end learnt image compression via non-local attention optimization and improved context modeling. IEEE Transactions on Image Processing 30 (2021), 3179–3191.Google ScholarCross Ref
- [18] . 2020. Learned image compression with discretized gaussian mixture likelihoods and attention modules. In CVPR. 7939–7948.Google ScholarCross Ref
- [19] . 2020. An overview of the MPEG-5 essential video coding standard [standards in a nutshell]. IEEE Signal Processing Magazine 37, 3 (2020), 160–167.Google ScholarCross Ref
- [20] . 2019. Variable rate deep image compression with a conditional autoencoder. In ICCV. 3146–3154.Google ScholarCross Ref
- [21] . 2021. Asymmetric gained deep image compression with continuous rate adaptation. In CVPR. 10532–10541.Google ScholarCross Ref
- [22] . 2019. Neural inter-frame compression for video coding. In ICCV. 6421–6429.Google ScholarCross Ref
- [23] . 2015. Compression artifacts reduction by a deep convolutional network. In ICCV. 576–584.Google ScholarDigital Library
- [24] . 2000. Efficient, robust, and fast global motion estimation for video coding. IEEE Transactions on Image Processing 9, 3 (2000), 497–501.Google ScholarDigital Library
- [25] . 2021. CNN-based depth map prediction for fast block partitioning in HEVC intra coding. In ICME. IEEE, 1–6.Google ScholarCross Ref
- [26] . 2023. Partition map prediction for fast block partitioning in VVC intra-frame coding. IEEE Transactions on Image Processing 32 (2023), 2237–2251.Google ScholarDigital Library
- [27] . 2023. NVTC: Nonlinear vector transform coding. In CVPR. 6101–6110.Google ScholarCross Ref
- [28] . 2022. Flexible neural image compression via code editing. In NeurIPS, Vol. 35. 12184–12196.Google Scholar
- [29] . 2019. MFQE 2.0: A new approach for multi-frame quality enhancement on compressed video. IEEE Transactions on Pattern Analysis and Machine Intelligence 43, 3 (2019), 949–963.Google ScholarCross Ref
- [30] . 2021. Causal contextual prediction for learned image compression. IEEE Transactions on Circuits and Systems for Video Technology 32, 4 (2021), 2329–2341.Google ScholarCross Ref
- [31] . 2021. Soft then hard: Rethinking the quantization in neural image compression. In ICML. 3920–3929.Google Scholar
- [32] . 2019. Video compression with rate-distortion autoencoders. In ICCV. 7033–7042.Google ScholarCross Ref
- [33] . 2021. A technical overview of AV1. Proc. IEEE 109, 9 (2021), 1435–1462.Google ScholarCross Ref
- [34] . 2022. ELIC: Efficient learned image compression with unevenly grouped space-channel contextual adaptive coding. In CVPR. 5718–5727.Google ScholarCross Ref
- [35] . 2021. Checkerboard context model for efficient learned image compression. In CVPR. 14771–14780.Google ScholarCross Ref
- [36] . 2020. Lossy image compression with normalizing flows. arXiv preprint arXiv:2008.10486 (2020).Google Scholar
- [37] . 2006. Reducing the dimensionality of data with neural networks. Science 313, 5786 (2006), 504–507.Google ScholarCross Ref
- [38] . 2022. CANF-VC: Conditional augmented normalizing flows for video compression. In ECCV. Springer, 207–223.Google ScholarDigital Library
- [39] . 2022. Learning end-to-end lossy image compression: A benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 8 (2022), 4194–4211.Google ScholarDigital Library
- [40] . 2020. Improving deep video compression by resolution-adaptive flow coding. In ECCV. Springer, 193–209.Google ScholarDigital Library
- [41] . 2022. Coarse-to-fine deep video coding with hyperprior-guided mode prediction. In CVPR. 5921–5930.Google ScholarCross Ref
- [42] . 2021. FVC: A new framework towards deep video compression in feature space. In CVPR. 1502–1511.Google ScholarCross Ref
- [43] . 2021. Deep network-based frame extrapolation with reference frame alignment. IEEE Transactions on Circuits and Systems for Video Technology 31, 3 (2021), 1178–1192.Google ScholarCross Ref
- [44] . 2018. Convolutional neural network-based motion compensation refinement for video coding. In ISCAS. IEEE, 1–4.Google ScholarCross Ref
- [45] . 1993. ISO/IEC 11172-2 (MPEG-I): Coding of Moving Pictures and Associated Audio for Digital Storage Media at up to About 1.5 Mbit/s - Part 2: Video.Google Scholar
- [46] . 1984. ITU-T Recommendation H.120: Codec for Videoconferencing Using Primary Digital Group Transmission.Google Scholar
- [47] . 1990. ITU-T Recommendation H.261: Video Codec for Audiovisual Services at p \(\times\) 64 kbitis.Google Scholar
- [48] . 1995. ITU-T Recommendation H.263: Video Coding for Low Bitrate Communication.Google Scholar
- [49] . 1994. ITU-T Recommendation H.262 - ISO/IEC 13818-2 (MPEG-2): Generic Coding of Moving Pictures and Associated Audio Information - Part 2: Video.Google Scholar
- [50] . 2019. Content-aware convolutional neural network for in-loop filtering in high efficiency video coding. IEEE Transactions on Image Processing 28, 7 (2019), 3343–3356.Google ScholarDigital Library
- [51] . 2022. Online meta adaptation for variable-rate learned image compression. In CVPR. 498–506.Google ScholarCross Ref
- [52] . 2021. VVC in-loop filters. IEEE Transactions on Circuits and Systems for Video Technology 31, 10 (2021), 3907–3925.Google ScholarCross Ref
- [53] . 2018. Fast CU depth decision for HEVC using neural networks. IEEE Transactions on Circuits and Systems for Video Technology 29, 5 (2018), 1462–1473.Google ScholarDigital Library
- [54] . 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014).Google Scholar
- [55] . 2022. Contextformer: A transformer with spatio-channel attention for context modeling in learned image compression. In ECCV. Springer, 447–463.Google ScholarDigital Library
- [56] . 2015. Deep learning. Nature 521, 7553 (2015), 436–444.Google ScholarCross Ref
- [57] . 2022. Selective compression learning of latent representations for variable-rate image compression. In NeurIPS, Vol. 35. 13146–13157.Google Scholar
- [58] . 2021. Deep contextual video compression. In NeurIPS, Vol. 34. 18114–18125.Google Scholar
- [59] . 2022. Hybrid spatial-temporal entropy modelling for neural video compression. In ACM Multimedia. 1503–1511.Google ScholarDigital Library
- [60] . 2023. Neural video compression with diverse contexts. In CVPR. 22616–22626.Google ScholarCross Ref
- [61] . 2018. Fully connected network-based intra prediction for image coding. IEEE Transactions on Image Processing 27, 7 (2018), 3236–3247.Google ScholarCross Ref
- [62] . 2018. An efficient four-parameter affine motion model for video coding. IEEE Transactions on Circuits and Systems for Video Technology 28, 8 (2018), 1934–1948.Google ScholarDigital Library
- [63] . 2023. Learning context-based nonlocal entropy modeling for image compression. IEEE Transactions on Neural Networks and Learning Systems 34, 3 (2023), 1132–1145.Google ScholarCross Ref
- [64] . 2001. Edge-directed prediction for lossless compression of natural images. IEEE Transactions on Image Processing 10, 6 (2001), 813–817.Google ScholarDigital Library
- [65] . 2019. Learning a convolutional neural network for image compact-resolution. IEEE Transactions on Image Processing 28, 3 (2019), 1092–1107.Google ScholarCross Ref
- [66] . 2021. Neural-network-based cross-channel intra prediction. ACM Trans. Multimedia Comput. Commun. Appl. 17, 3, Article
77 (Jul. 2021), 23 pages.Google ScholarDigital Library - [67] . 2022. Content-adaptive motion rate adaption for learned video compression. In PCS. 163–167.Google ScholarCross Ref
- [68] . 2020. M-LVC: Multiple frames prediction for learned video compression. In CVPR. 3546–3554.Google ScholarCross Ref
- [69] . 2020. Deep learning-based technology in responses to the joint call for proposals on video compression with capability beyond HEVC. IEEE Transactions on Circuits and Systems for Video Technology 30, 5 (2020), 1267–1280.Google ScholarCross Ref
- [70] . 2020. Deep learning-based video coding: A review and a case study. ACM Computing Surveys (CSUR) 53, 1 (2020), 1–35.Google ScholarDigital Library
- [71] . 2018. CNN-based DCT-like transform for image compression. In MMM. Springer, 61–72.Google ScholarCross Ref
- [72] . 2008. Manipulating image patches for compression. In ICME. 197–200.Google ScholarCross Ref
- [73] . 2015. Local Illumination Compensation.
Technical Report VCEG-AZ06. VCEG.Google Scholar - [74] . 2021. Neural video coding using multiscale motion compensation and spatiotemporal context model. IEEE Transactions on Circuits and Systems for Video Technology 31, 8 (2021), 3182–3196.Google ScholarCross Ref
- [75] . 2020. A comprehensive benchmark for single image compression artifact reduction. IEEE Transactions on Image Processing 29 (2020), 7845–7860.Google ScholarCross Ref
- [76] . 2023. Learned image compression with mixed transformer-CNN architectures. In CVPR. 14388–14397.Google ScholarCross Ref
- [77] . 2020. Conditional entropy coding for efficient video compression. In ECCV. Springer, 453–468.Google ScholarDigital Library
- [78] . 2021. Context-adaptive inverse quantization for inter-frame coding. IEEE Open Journal of Circuits and Systems 2 (2021), 660–674.Google ScholarCross Ref
- [79] . 1996. A block-based gradient descent search algorithm for block motion estimation in video coding. IEEE Transactions on Circuits and Systems for Video Technology 6, 4 (1996), 419–422.Google ScholarDigital Library
- [80] . 2023. Deep multi-task learning based fast intra-mode decision for versatile video coding. IEEE Transactions on Circuits and Systems for Video Technology 33, 10 (2023), 6101–6116.Google ScholarDigital Library
- [81] . 2016. CU partition mode decision for HEVC hardwired intra encoder using convolution neural network. IEEE Transactions on Image Processing 25, 11 (2016), 5088–5103.Google ScholarDigital Library
- [82] . 2020. Content adaptive and error propagation aware deep video compression. In ECCV. 456–472.Google ScholarDigital Library
- [83] . 2019. DVC: An end-to-end deep video compression framework. In CVPR. 11006–11015.Google ScholarCross Ref
- [84] . 2019. Convolutional neural network-based arithmetic coding for HEVC intra-predicted residues. IEEE Transactions on Circuits and Systems for Video Technology 30, 7 (2019), 1901–1916.Google Scholar
- [85] . 2021. End-to-end image compression with probabilistic decoding. arXiv preprint arXiv:2109.14837 (2021).Google Scholar
- [86] . 2020. Improving compression artifact reduction via end-to-end learning of side information. In VCIP. 403–406.Google ScholarCross Ref
- [87] . 2019. iWave: CNN-based wavelet-like transform for image compression. IEEE Transactions on Multimedia 22, 7 (2019), 1667–1679.Google ScholarCross Ref
- [88] . 2022. End-to-end optimized versatile image compression with wavelet-like transform. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 3 (2022), 1247–1263.Google ScholarCross Ref
- [89] . 2020. MPEG-5 Part 2: Low complexity enhancement video coding (LCEVC): Overview and performance evaluation. In Applications of Digital Image Processing XLIII, Vol. 11510. International Society for Optics and Photonics, 115101C.Google Scholar
- [90] . 2018. Conditional probability models for deep image compression. In CVPR. 4394–4402.Google ScholarCross Ref
- [91] . 2022. VCT: A video compression transformer. In NeurIPS, Vol. 35. 13091–13103.Google Scholar
- [92] . 2018. Joint autoregressive and hierarchical priors for learned image compression. In NIPS, Vol. 31. 10794–10803.Google Scholar
- [93] . 2020. Channel-wise autoregressive entropy models for learned image compression. In ICIP. IEEE, 3339–3343.Google ScholarCross Ref
- [94] . 2006. Numerical Optimization. Springer Science & Business Media.Google Scholar
- [95] . 2012. Comparison of the coding efficiency of video coding standards-including high efficiency video coding (HEVC). IEEE Transactions on Circuits and Systems for Video Technology 22, 12 (2012), 1669–1684.Google ScholarDigital Library
- [96] . 1998. Rate-distortion methods for image and video compression. IEEE Signal Processing Magazine 15, 6 (1998), 23–50.Google ScholarCross Ref
- [97] . 2022. Content adaptive latents and decoder for neural image compression. In ECCV. Springer, 556–573.Google ScholarDigital Library
- [98] . 2016. Overview of screen content video coding: Technologies, standards, and beyond. IEEE Journal on Emerging and Selected Topics in Circuits and Systems 6, 4 (2016), 393–408.Google ScholarCross Ref
- [99] . 2018. Neural network based intra prediction for video coding. In Applications of Digital Image Processing XLI, Vol. 10752. International Society for Optics and Photonics, 1075213.Google ScholarCross Ref
- [100] . 2009. Novel directional gradient descent searches for fast block motion estimation. IEEE Transactions on Circuits and Systems for Video Technology 19, 8 (2009), 1189–1195.Google ScholarDigital Library
- [101] . 2022. Entroformer: A transformer-based entropy model for learned image compression. arXiv preprint arXiv:2202.05492 (2022).Google Scholar
- [102] . 2021. ELF-VC: Efficient learned flexible-rate video coding. In ICCV. 14479–14488.Google ScholarCross Ref
- [103] . 2019. Learned video compression. In ICCV. 3454–3463.Google ScholarCross Ref
- [104] . 1948. A mathematical theory of communication. Bell Systems Technical Journal 27, 4 (1948), 623–656.Google ScholarCross Ref
- [105] . 1959. Coding theorems for a discrete source with a fidelity criteria. International Convention Record 7 (1959), 325–350.Google Scholar
- [106] . 2023. Temporal context mining for learned video compression. IEEE Transactions on Multimedia 25 (2023), 7311–7322.Google ScholarDigital Library
- [107] . 2022. AlphaVC: High-performance and efficient learned video compression. In ECCV. Springer, 616–631.Google ScholarDigital Library
- [108] . 2005. Trends and perspectives in image and video coding. Proc. IEEE 93, 1 (2005), 6–17.Google ScholarCross Ref
- [109] . 2013. The SJTU 4K video sequence dataset. In QoMEX. 34–35.Google ScholarCross Ref
- [110] . 2021. Variable-rate deep image compression through spatially-adaptive feature transform. In ICCV. 2360–2369.Google ScholarCross Ref
- [111] . 2022. FastInter360: A fast inter mode decision for HEVC 360 video coding. IEEE Transactions on Circuits and Systems for Video Technology 32, 5 (2022), 3235–3249.Google ScholarDigital Library
- [112] . 2012. Overview of the high efficiency video coding (HEVC) standard. IEEE Transactions on Circuits and Systems for Video Technology 22, 12 (2012), 1649–1668.Google ScholarDigital Library
- [113] . 1998. Rate-distortion optimization for video compression. IEEE Signal Processing Magazine 15, 6 (1998), 74–90.Google ScholarCross Ref
- [114] . 2022. Improving latent quantization of learned image compression with gradient scaling. In VCIP. 1–5.Google ScholarCross Ref
- [115] . 2022. Joint graph attention and asymmetric convolutional neural network for deep image compression. IEEE Transactions on Circuits and Systems for Video Technology 33, 1 (2022), 421–433.Google ScholarCross Ref
- [116] . 2021. On the advantages of stochastic encoders. arXiv preprint arXiv:2102.09270 (2021).Google Scholar
- [117] . 2017. Lossy image compression with compressive autoencoders. arXiv preprint arXiv:1703.00395 (2017).Google Scholar
- [118] . 2015. Variable rate image compression with recurrent neural networks. arXiv preprint arXiv:1511.06085 (2015).Google Scholar
- [119] . 2013. Adaptive loop filtering for video coding. IEEE Journal of Selected Topics in Signal Processing 7, 6 (2013), 934–945.Google ScholarCross Ref
- [120] . 2021. Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set. arXiv preprint arXiv:2111.10302 (2021).Google Scholar
- [121] . 2008. Adaptive interpolation filter for H. 264/AVC. IEEE Transactions on Circuits and Systems for Video Technology 19, 2 (2008), 179–192.Google ScholarDigital Library
- [122] . 1992. The JPEG still picture compression standard. IEEE Transactions on Consumer Electronics 38, 1 (1992), xviii–xxxiv.Google ScholarDigital Library
- [123] . 2022. Neural data-dependent transform for learned image compression. In CVPR. 17379–17388.Google ScholarCross Ref
- [124] . 2022. Substitutional neural image compression. In PCS. 97–101.Google ScholarCross Ref
- [125] . 2020. Ensemble learning-based rate-distortion optimization for end-to-end image compression. IEEE Transactions on Circuits and Systems for Video Technology 31, 3 (2020), 1193–1207.Google ScholarCross Ref
- [126] . 2002. Video Processing and Communications. Vol. 1. Prentice Hall Upper Saddle River, NJ.Google Scholar
- [127] . 2006. Adaptive interpolation filters and high-resolution displacements for video coding. IEEE Transactions on Circuits and Systems for Video Technology 16, 4 (2006), 484–491.Google ScholarDigital Library
- [128] . 2003. Rate-constrained coder control and comparison of video coding standards. IEEE Transactions on Circuits and Systems for Video Technology 13, 7 (2003), 688–703.Google ScholarDigital Library
- [129] . 2003. Overview of the H.264/AVC video coding standard. IEEE Transactions on Circuits and Systems for Video Technology 13, 7 (2003), 560–576.Google ScholarDigital Library
- [130] . 1998. Piecewise 2D autoregression for predictive image coding. In ICIP. IEEE, 901–904.Google Scholar
- [131] . 2021. Enhanced invertible encoding for learned image compression. In ACM Multimedia. 162–170.Google ScholarDigital Library
- [132] . 2018. Reducing complexity of HEVC: A deep learning approach. IEEE Transactions on Image Processing 27, 10 (2018), 5044–5059.Google ScholarCross Ref
- [133] . 2023. Bit allocation using optimization. In ICML. 38377–38399.Google Scholar
- [134] . 2019. Invertibility-driven interpolation filter for video coding. IEEE Transactions on Image Processing 28, 10 (2019), 4912–4925.Google ScholarCross Ref
- [135] . 2020. Deep learning-based nonlinear transform for HEVC intra coding. In VCIP. 387–390.Google ScholarCross Ref
- [136] . 2021. Knowledge distillation from end-to-end image compression to VVC intra coding for perceptual quality enhancement. In ICIP. 3438–3442.Google ScholarCross Ref
- [137] . 2020. Learning for video compression with hierarchical quality and recurrent enhancement. In CVPR. 6628–6637.Google ScholarCross Ref
- [138] . 2020. Learning for video compression with recurrent auto-encoder and recurrent probability model. IEEE Journal of Selected Topics in Signal Processing 15, 2 (2020), 388–401.Google ScholarCross Ref
- [139] . 2020. Improving inference for neural image compression. In NeurIPS, Vol. 33. 573–584.Google Scholar
- [140] . 1999. Least squares approach for lossless image coding. In International Symposium on Signal Processing and its Applications (ISSPA), Vol. 1. IEEE, 63–66.Google ScholarCross Ref
- [141] . 2010. Model based motion vector predictor for zoom motion. IEEE Signal Processing Letters 17, 9 (2010), 787–790.Google ScholarCross Ref
- [142] . 2012. Affine model based motion compensation prediction for zoom. IEEE Transactions on Multimedia 14, 4 (2012), 1370–1375.Google ScholarDigital Library
- [143] . 2022. End-to-end rate-distortion optimized learned hierarchical bi-directional video compression. IEEE Transactions on Image Processing 31 (2022), 974–983.Google ScholarDigital Library
- [144] . 2021. Learn to overfit better: Finding the important parameters for learned image compression. In VCIP. IEEE, 1–5.Google ScholarCross Ref
- [145] . 2019. Recent development of AVS video coding standard: AVS3. In PCS. IEEE, 1–5.Google ScholarCross Ref
- [146] . 2018. Enhanced cross-component linear model for chroma intra-prediction in video coding. IEEE Transactions on Image Processing 27, 8 (2018), 3983–3997.Google ScholarCross Ref
- [147] . 2023. LVQAC: Lattice vector quantization coupled with spatially adaptive companding for efficient learned image compression. In CVPR. 10239–10248.Google ScholarCross Ref
- [148] . 2021. Improving VVC intra coding via probability estimation and fusion of multiple prediction modes. In ICIG. Springer, 654–664.Google ScholarDigital Library
- [149] . 2021. A universal encoder rate distortion optimization framework for learned compression. In CVPR. 1880–1884.Google ScholarCross Ref
- [150] . 2019. Enhanced bi-prediction with convolutional neural network for high efficiency video coding. IEEE Transactions on Circuits and Systems for Video Technology 29, 11 (2019), 3291–3301.Google ScholarDigital Library
- [151] . 2020. Channel-level variable quantization network for deep image compression. In IJCAI. 467–473.Google ScholarCross Ref
- [152] . 2022. Unified multivariate Gaussian mixture for efficient neural image compression. In CVPR. 17612–17621.Google ScholarCross Ref
- [153] . 2022. Transformer-based transform coding. In ICLR. https://openreview.net/forum?id=IDwN6xjHnK8Google Scholar
- [154] . 2020. L2C – learning to learn to compress. In MMSP. 1–6.Google Scholar
- [155] . 2022. The devil is in the details: Window-based attention for image compression. In CVPR. 17492–17501.Google ScholarCross Ref
Index Terms
- Towards Hybrid-Optimization Video Coding
Recommendations
SSIM-based error-resilient rate-distortion optimization of H.264/AVC video coding for wireless streaming
The SSIM-based rate-distortion optimization (RDO) has been verified to be an effective tool for H.264/AVC to promote the perceptual video coding performance. However, the current SSIM-based RDO is not efficient for improving the perceptual quality of ...
Rate-distortion optimized rate-allocation for motion-compensated predictive video codecs using PixelRank
Inter-frame dependencies are usually ignored in video encoder coding parameter selection. This gives a non-optimal solution and degrades the compression performance. A mathematical model to estimate the importance of each pixel on the reconstructed ...
Video coding optimization in AVS2
AbstractChinese second generation of the Audio Video Coding Standard, known as the AVS2, competing with HEVC/H.265 and AV1, has become a well-known video compression standard. Many unique tools have been developed and incorporated in AVS2. ...
Highlights- A frame level QP and λ allocation named reference structure determined parameter (RSDP) algorithm is proposed to satisfy GoP length 4, 8, and 16 ...
Comments