Neural-Network Tone Mapping for Brightness and Energy Balance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing video coding systems lack efficient methods for tone mapping that adapt to brightness changes and energy consumption, leading to suboptimal video quality and efficiency.

Innovation Solution

Implementing a neural-network post-filter (NNPF) for tone mapping, which determines metadata parameters based on brightness adaptation and energy consumption events, and includes a tone mapping indication in video data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If neural-network post-filter (NNPF) for tone mapping is applied to adapt to brightness changes, then video quality is improved, but energy consumption increases

Engineering Contradiction:
Improvevideo qualityVSAvoidenergy consumption
Core Design Contradiction:
Manufacturing precisionVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts the application of NNPF tone mapping based on detected brightness changes. The decoder determines whether to apply NNPF by evaluating brightness adaptation needs, allowing the system to adapt its processing intensity to actual content requirements rather than applying fixed processing to all video data.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes processing parameters (applying or not applying NNPF) based on detected brightness events. Metadata parameters indicate when tone mapping should be applied, allowing the system to modify its operational state according to content characteristics and brightness change events.

Inventive Principle:
Principle #35Parameter changes

2Loss of energy

If neural-network post-filter (NNPF) for tone mapping is applied to optimize energy consumption, then energy efficiency is improved, but video quality may deteriorate

Engineering Contradiction:
Improveenergy efficiencyVSAvoidvideo quality
Core Design Contradiction:
Loss of energyVSManufacturing precision

Solution Approach 1:

The system uses metadata parameters to control when NNPF is applied, changing the processing state based on energy consumption events and brightness adaptation needs. This allows selective application of tone mapping only when beneficial for energy efficiency while maintaining acceptable video quality.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system detects brightness changes and energy consumption events, then uses this feedback to determine whether to apply NNPF tone mapping. The decoder evaluates the detected events and adjusts processing accordingly, creating a closed-loop system that balances quality and energy efficiency based on real-time conditions.

Inventive Principle:
Principle #23Feedback

3Illumination intensity

If brightness adaptation through tone mapping is applied, then brightness uniformity is improved, but processing complexity increases

Engineering Contradiction:
Improvebrightness uniformityVSAvoidprocessing complexity
Core Design Contradiction:
Illumination intensityVSDevice complexity

Solution Approach 1:

The system uses metadata as an intermediary to control the application of NNPF tone mapping. Rather than continuously analyzing brightness and making processing decisions, the metadata provides pre-computed guidance on when and how to apply tone mapping, simplifying the decoder's processing complexity while achieving brightness uniformity.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The encoder performs preliminary analysis and determines tone mapping parameters in advance, encoding this information in metadata. The decoder then simply follows these pre-determined instructions rather than performing complex real-time analysis, reducing processing complexity while maintaining brightness adaptation capability.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4676060A1Neural network post filter for tone mapping
Publication Date: 2026.01.07 INTERDIGITAL CE PATENT HOLDINGS SAS
  • EP4676060A1 patent drawingFigure 1A
  • EP4676060A1 patent drawingFigure 1B
  • EP4676060A1 patent drawingFigure 1C

AI summary

A video encoding device may determine whether to apply neural-network post-filter (NNPF) for tone mapping. The device may, based on a determination to apply NNPF, obtain at least one metadata parameter associated with NNPF tone mapping. The device may include, in video data, a neural-network post-filter tone mapping indication that NNPF for tone mapping is to be applied. A video decoding device may determine whether to apply NNPF for tone mapping based on a neural-network post-filter tone mapping indication. The device may, based on a determination to apply NNPF, determine at least one metadata parameter associated with NNPF tone mapping. The device may apply NNPF for tone mapping based on the at least one metadata parameter. The device may obtain an NNPF characteristics (NNPFC) tone mapping sub-purpose indication. The at least one metadata parameter associated with NNPF tone mapping may be determined based on the NNPFC tone mapping sub-purpose indication.