High Dynamic Range Image Reconstruction via Deep Explicit Polynomial Curve Estimation
Not on the map. Why?
Abstract (arXiv)
Due to limited camera capacities, digital images usually have a narrower dynamic illumination range than real-world scene radiance. To resolve this problem, High Dynamic Range (HDR) reconstruction is proposed to recover the dynamic range to better represent real-world scenes. However, due to different physical imaging parameters, the tone-mapping functions between images and real radiance are highly diverse, which makes HDR reconstruction extremely challenging. Existing solutions can not explicitly clarify a corresponding relationship between the tone-mapping function and the generated HDR image, but this relationship is vital when guiding the reconstruction of HDR images. To address this problem, we propose a method to explicitly estimate the tone mapping function and its corresponding HDR image in one network. Firstly, based on the characteristics of the tone mapping function, we construct a model by a polynomial to describe the trend of the tone curve. To fit this curve, we use a learnable network to estimate the coefficients of the polynomial. This curve will be automatically adjusted according to the tone space of the Low Dynamic Range (LDR) image, and reconstruct the real HDR image. Besides, since all current datasets do not provide the corresponding relationship between the tone mapping function and the LDR image, we construct a new dataset with both synthetic and real images. Extensive experiments show that our method generalizes well under different tone-mapping functions and achieves SOTA performance.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 33 references that are in the map. First posted on arXiv 31 Jul 2023.
Builds on
16 of 33 references.
References · 16
- 2017Attention Is All You Needcited by 59,932
- 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
- 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
- 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
- 2018Toward Convolutional Blind Denoising of Real Photographscited by 274
- 2021Unsupervised Degradation Representation Learning for Blind Super-Resolutioncited by 177
- 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
- 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
- 2019Attention-guided Network for Ghost-free High Dynamic Range Imagingcited by 116
- 2021Blind Image Super-Resolution: A Survey and Beyondcited by 93
- 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
- 2021HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantizationcited by 58
4 more
- 2021NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Resultscited by 36
- 2019GAN2GAN: Generative Noise Learning for Blind Denoising with Single Noisy Imagescited by 12
- 2021HDR-cGAN: Single LDR to HDR Image Translation using Conditional GANcited by 7
- 2021MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstructioncited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.