Arithmetic Bitstream Entry Points to Break Sequential CABAC Decoding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing arithmetic decoding processes, such as context-based adaptive binary arithmetic coding (CABAC), are highly sequential and cannot be parallelized, limiting decoding speed.

Innovation Solution

An encoding and decoding concept that allows for parallel decoding by providing entry point information in the bitstream, enabling multiple decoders to operate on different parts of the bitstream simultaneously, and includes an arithmetic encoder and decoder that renormalize internal parameters and use subintervals based on probability estimates to resume decoding from a predetermined point.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If arithmetic decoding is performed using a sequential process (CABAC), then decoding accuracy is maintained, but decoding speed is limited

Engineering Contradiction:
Improvedecoding speedVSAvoidcoding procedure complexity
Core Design Contradiction:
SpeedVSDevice complexity

Solution Approach 1:

The bitstream is divided into multiple segments with entry points, allowing multiple decoders to work on different segments simultaneously. Each segment contains sufficient information (entry point information) for independent decoding, enabling parallel processing while maintaining decoding accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Entry point information is prepared and embedded in the bitstream during encoding, so that decoders can directly jump to predetermined positions without sequential processing. This preliminary preparation enables parallel decoding to start immediately at multiple entry points.

Inventive Principle:
Principle #10Preliminary action

2Productivity

If multiple decoders operate in parallel on different parts of the bitstream, then decoding speed is improved, but coordination and resynchronization become complex

Engineering Contradiction:
Improvedecoding efficiencyVSAvoiddecoder coordination complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The bitstream is segmented into independent decoding regions marked by entry points. Each decoder operates on its assigned segment with a predetermined starting position, eliminating the need for complex inter-decoder coordination while enabling parallel processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

Each decoder is equipped with entry point information that allows it to independently locate and start decoding at the correct position in the bitstream. This self-service capability eliminates the need for external synchronization mechanisms between parallel decoders.

Inventive Principle:
Principle #25Self-service

3Speed

If entry point information is added to the bitstream to enable parallel decoding, then decoding speed is enhanced, but bitstream size increases

Engineering Contradiction:
Improvedecoding speedVSAvoidbitstream size
Core Design Contradiction:
SpeedVSQuantity of substance

Solution Approach 1:

Instead of adding extensive synchronization data, only essential entry point information (position markers) is added to the bitstream. This minimal addition provides sufficient information for parallel decoding without significantly increasing bitstream size.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20250365010A1Arithmetic encoder for arithmetically encoding and arithmetic decoder for arithmetically decoding a sequence of information values, methods for arithmetically encoding and decoding a sequence of information values and computer program for implementing these methods
Publication Date: 2025.11.27 FRAUNHOFER GESELLSCHAFT ZUR FORDERUNG DER ANGEWANDTEN FORSCHUNG EV
  • US20250365010A1 patent drawing
  • US20250365010A1 patent drawing
  • US20250365010A1 patent drawing

AI summary

An encoding scheme is provided for arithmetically encoding a sequence of information values into an arithmetic coded bitstream by providing the bitstream with entry point information, allowing for resuming arithmetic decoding of the bitstream from a predetermined entry point onward. A respective decoding scheme is also provided. These encoding and decoding schemes provide more efficient encoding in view of the decoding speed.