G-SemTMO: Tone Mapping With a Trainable Semantic Graph

Abhishek Goswami

doi:10.1109/ACCESS.2024.3491494

2024-01-01

DOI：10.1109/ACCESS.2024.3491494

原文链接

原文求助

摘要

En 中文

A Tone Mapping Operator (TMO) is required to render images with a High Dynamic Range (HDR) on media with limited dynamic capabilities. TMOs compress the dynamic range with the aim of preserving the visually perceptual cues of the scene. Previous literature has established the benefits of TMOs being semantic-aware and understanding the content in the scene to preserve cues better. Expert photographers analyze the semantic and contextual information of a scene and decide tonal transformations or local luminance adjustments. This process can be considered a manual analogy to tone mapping. In this work, we draw inspiration from an expert photographer's approach and present a Graph-based Semantic-aware Tone Mapping Operator, G-SemTMO. We leverage semantic information as well as the contextual information of the scene in the form of a graph capturing the spatial arrangements of its semantic segments. Using Graph Convolutional Network (GCN), we predict intermediate parameters called Semantic Hints and use these parameters to apply tonal adjustments locally to different semantic segments in the image. In addition, we also introduce LocHDR, a dataset of 781 HDR images tone mapped manually by an expert photo-retoucher with local tonal enhancements. We conduct ablation studies to show that our approach, G-SemTMO, can learn both global and local tonal transformations from a pair of input linear and manually retouched images by leveraging the semantic graphs and produce better results than both traditional and learning based TMOs. We also conduct ablation experiments to validate the advantage of using GCN.

Keyword:

Deep learning

graph convolutional networks

semantic awareness

HDR tone mapping operators

期刊

IEEE Access

IF:

3.6

论文数:

9.8W

被引数:

29.4W

机构

centre national de la recherche scientifique (cnrs)

学者数:

24.5W

论文数: 18.2W

被引数: 279

University of Cambridge

学者数:

7.7W

论文数: 7.1W

被引数: 13.7W

Universite Paris Saclay

学者数:

7.3W

论文数: 5.3W

被引数: 540

University of Warwick

学者数:

2.2W

论文数: 2.2W

被引数: 85

查看更多机构

引用论文

Combined resistive and laser heating technique for in situ radial X-ray diffraction in the diamond anvil cell at high pressure and temperature

Review of Scientific Instruments

IF0

2013-02-28

OAAI

Lowell Miyagi; Waruntorn Kanitpanyacharoen; Selva Vennila Raju; Pamela Kaercher; Jason Knight; Alastair MacDowell; Hans-Rudolf Wenk; Quentin Williams; Eloisa Zepeda Alarcon

RESOLUTION OF INTRAVITREAL CLOTS BY UROKINASE

The Lancet

IF0

1973-07-01

PREAI

John Forrester; John Williamson

Deep Tone Mapping Operator for High Dynamic Range Images

IEEE TRANSACTIONS ON IMAGE PROCESSING

IF13.7

2020-01-01

OAAI

Rana, Aakanksha; Singh, Praveer; Valenzise, Giuseppe; Dufaux, Frederic; Komodakis, Nikos; Smolic, Aljosa