Context-based adaptive binary arithmetic coding in the H.264/AVC video compression standard

By Detlev Marpe, Thomas Wiegand, Heiko Schwarz. 2003

1,361 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Signal Processing

Citations in the corpus

End-to-end Optimized Image Compression (2016, methodology): “We follow a simple scheme inspired by the encoding of H.264/AVC transform coefﬁcients as detailed by Marpe, Schwarz, and Wiegand (2003).”
High-Fidelity Generative Image Compression (2020, methodology): “, arithmetic coding [30]), we can store y losslessly using bitrate r(y) = − log(P (y)) (in practice there is a negligible bit-overhead incurred by the entropy coder).”
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations (2017, methodology): “Furthermore, they model marginals for entropy estimation using linear splines and also use CABAC[21] coding.”
Analysis, fast algorithm, and VLSI architecture design for H.264/AVC intra frame coder (2005, methodology): “The proposed complexity reduction methods are simple and effective.”
Conditional Probability Models for Deep Image Compression (2018, methodology): “as the coding cost of the latent image representation, since this reflects the coding cost incurred when using P as a context model with an adaptive arithmetic encoder [11].”
CompressAI: a PyTorch library and evaluation platform for end-to-end compression research (2020, neutral): “…frequencies with linear transforms ( e.g. : DCT or DWT), perform some predictions based on neighboring values, quantize the transformed coefﬁcients, and ﬁnally encode the quantized values and the prediction side-information into a bit-stream with an efﬁcient entropy coder ( e.g. : CABAC [11]).”
Asymmetric numeral systems: entropy coding combining speed of Huffman coding with compression rate of arithmetic coding (2013, methodology): “It can be applied similarly like one of many AC approximations, for example M coder used in CABAC [8] in modern video compression.”
The Devil Is in the Details: Window-based Attention for Image Compression (2022, methodology): “After quantization, entropy estimation modules predict the distributions of latents, then the lossless Context-based Adaptive Binary Arithmetic Coding (CABAC) [30] or Range Coder [31] compresses the latents into the bit stream.”
Analysis and architecture design of an HDTV720p 30 frames/s H.264/AVC encoder (2006, background): “Moreover, the advanced entropy coding tools [9] use content adaptivity to reduce more statistic redundancy.”
Checkerboard Context Model for Efficient Learned Image Compression (2021, methodology): “Common image compression algorithms like JPEG [15], JPEG2000 [30] and BPG [8] all follow a general pipeline, where lossless entropy coders [23] are used after image transformations and quantization.”
Video coding with H.264/AVC: tools, performance, and complexity (2004, background): “More details on CABAC can be found in [16].”
HEVC Complexity and Implementation Analysis (2012, methodology): “In the case of a single-core implementation for tiles, the extra overhead comes in the form of more complicated boundary condition checking, performing a CABAC reset for each tile and the need to perform the optional filtering of tile boundaries.”
Overview of the H.264/AVC video coding standard (2003, methodology): “More details on CABAC can be found in [ 16 ].”
Practical Full Resolution Learned Lossless Image Compression (2018, neutral): “Classical approaches are discussed in [22, 24, 25, 46, 44].”