Unpaired Learning for High Dynamic Range Image Tone Mapping

  title={Unpaired Learning for High Dynamic Range Image Tone Mapping},
  author={Yael Vinker and Inbar Huberman-Spiegelglas and Raanan Fattal},
  journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
High dynamic range (HDR) photography is becoming increasingly popular and available by DSLR and mobile-phone cameras. While deep neural networks (DNN) have greatly impacted other domains of image manipulation, their use for HDR tone-mapping is limited due to the lack of a definite notion of ground-truth solution, which is needed for producing training data.In this paper we describe a new tone-mapping approach guided by the distinct goal of producing low dynamic range (LDR) renditions that best… 

Figures and Tables from this paper

Perceptual Optimization of a Biologically-Inspired Tone Mapping Operator

This paper develops a two-stage neural network-based HDR image TMO that is biologically-inspired, computationally efficient, and perceptually optimized, and fully automatic to tone map uncalibrated HDR images.

Rendering Nighttime Image Via Cascaded Color and Brightness Compensation

  • Zhihao LiSi YiZhan Ma
  • Computer Science
    2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2022
The CBUnet is developed, a two-stage NN ISP to cascade the compensation of color and brightness attributes and is ranked at the second place in the NTIRE 2022 Night Photography Rendering Challenge.

Learning to Adapt to Light

This study proposes a biologically inspired method to handle light-related image-enhancement tasks with a unified network (called LA-Net) and demonstrates that the proposed method almost obtains state-of-the-art performance compared with recent methods designed for these individual tasks.

NTIRE 2022 Challenge on Night Photography Rendering

This paper reviews the NTIRE 2022 challenge on night photography rendering. The challenge solicited solutions that processed RAW camera images captured in night scenes to produce a photo-finished



A Generative Adversarial Network for Tone Mapping HDR Images

A novel generative adversarial network is proposed to learn a combination of these tone mapping operators and generates images with comparably high TMQI and indeed works on many different types of images.

Deep Learning for Robust end-to-end Tone Mapping

A new end-to-end tone mapping approach based on Deep Convolutional Adversarial Networks (DCGANs) is introduced along with a data augmentation technique, and shown to improve upon the latest state-of-the-art on benchmarking datasets.

Deep tone mapping network in HSV color space

A tone mapping network (TMNet) in Hue-Saturation-Value (HSV) color space to obtain better luminance and color mapping and can achieve better performance in both subjective and objective evaluations is proposed.

TMO-Net: A Parameter-Free Tone Mapping Operator Using Generative Adversarial Network, and Performance Benchmarking on Large Scale HDR Dataset

Experimental results demonstrate that the proposed TMO-Net qualitatively and quantitatively outperforms current state-of-the-art TMOs.

Adversarial and Adaptive Tone Mapping Operator for High Dynamic Range Images

This work proposes to deploy a conditional generative adversarial networks to build an adversarial and adaptive tone mapping operator (adTMO) that converts HDR into LDR images that outperforms all other contemporary tone mapping operators.

Deep high dynamic range imaging of dynamic scenes

A convolutional neural network is used as the learning model and three different system architectures are compared to model the HDR merge process to demonstrate the performance of the system by producing high-quality HDR images from a set of three LDR images.

EnlightenGAN: Deep Light Enhancement Without Paired Supervision

This paper proposes a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images.

High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs

A new method for synthesizing high-resolution photo-realistic images from semantic label maps using conditional generative adversarial networks (conditional GANs) is presented, which significantly outperforms existing methods, advancing both the quality and the resolution of deep image synthesis and editing.

Deep Feature Consistent Deep Image Transformations: Downscaling, Decolorization and HDR Tone Mapping

The Deep Feature Consistent Deep Image Transformation (DFC-DIT) framework is developed which unifies challenging one-to-many mapping image processing problems such as image downscaling, decolorization and high dynamic range (HDR) image tone mapping.

Blind Quality Assessment of Tone-Mapped Images Via Analysis of Information, Naturalness, and Structure

An effective and efficient no-reference objective quality metric which can automatically assess LDR images created by different TMOs without access to the original HDR images is developed.