Transformer-Based Image Reconstruction for Low-Light Super-Resolution

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing image super-resolution methods are not suitable for reconstructing real-world Low-Light Low-Resolution (LLLR) images due to their inability to effectively utilize global contextual information and long-range dependencies, leading to poor reconstruction accuracy and limited detail enhancement.

Innovation Solution

A novel transformer-based multi-scale hierarchical encoder-decoder network (RELIEF) is employed for joint Low-Light Enhancement (LLE) and Super-Resolution (SR), utilizing Cross-Shaped Window multi-headed self-attention mechanisms and Locally-enhanced Feed-Forward and Positional Encoding modules to capture long-range dependencies and local context, enhancing both spatial resolution and lightness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If CNN-based SR methods are used, then local detail reconstruction is improved, but global contextual information utilization is insufficient

Engineering Contradiction:
Improvelocal detail reconstruction accuracyVSAvoidglobal contextual information
Core Design Contradiction:
Manufacturing precisionVSLoss of information

Solution Approach 1:

The patent merges CNN and Transformer architectures into a hybrid model that combines local detail processing capabilities of CNNs with global contextual modeling capabilities of Transformers, thereby simultaneously improving local reconstruction accuracy and global information utilization

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces multi-scale feature extraction that processes images at different resolution levels, adding a dimensional aspect to feature representation that enables both local detail preservation and global context integration across multiple scales

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Illumination intensity

If sequential LLE and SR processing is applied, then exposure correction is achieved, but reconstruction accuracy deteriorates due to error accumulation

Engineering Contradiction:
Improveexposure correctionVSAvoidreconstruction accuracy
Core Design Contradiction:
Illumination intensityVSManufacturing precision

Solution Approach 1:

The patent combines LLE and SR into a single joint processing framework that simultaneously performs illumination correction and super-resolution, eliminating the sequential processing bottleneck and preventing error accumulation between stages

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent incorporates illumination correction as a preliminary step within the unified network architecture, preparing the input data for super-resolution processing while maintaining end-to-end optimization that prevents error propagation

Inventive Principle:
Principle #10Preliminary action

3Loss of information

If larger training patches are used, then global contextual information is improved, but computational complexity increases

Engineering Contradiction:
Improveglobal contextual informationVSAvoidcomputational complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments the computational process into encoder and decoder stages with intermediate feature representations, allowing large contextual information processing to be divided into manageable computational steps that reduce overall complexity

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies different processing strategies to different parts of the feature space, using lightweight operations for local feature extraction and more sophisticated transformations only where global context is most needed, thereby optimizing computational resource allocation

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4258204B1Image processing method, apparatus, computer program and computer-readable data carrier
Publication Date: 2025.10.29 MILESTONE SYSTEMS
  • EP4258204B1 patent drawingFigure 1A
  • EP4258204B1 patent drawingFigure 1B
  • EP4258204B1 patent drawingFigure 1C

AI summary

The invention provides an image processing method comprising: acquiring a first image whose spatial resolution and lightness are to be enhanced; generating a residual image from the first image using a multi-scale hierarchical neural network for joint learning of low-light enhancement and super-resolution, the network comprising an encoder stage and a decoder stage forming a plurality of symmetrical encoder-decoder levels, each encoder and decoder in each level comprising a vision transformer block; generating a reconstructed image based on the first and residual images.