Deep High Dynamic Range Imaging with Large Foreground Motions

By Shangzhe Wu, Jiarui Xu, Yu-Wing Tai, Chi-Keung Tang. European Conference on Computer Vision, 2017

301 citations recorded by the source corpus.

This paper proposes the first non-flow-based deep framework for high dynamic range (HDR) imaging of dynamic scenes with large-scale foreground motions. In state-of-the-art deep HDR imaging, input images are first aligned using optical flows before merging, which are still error-prone due to occlusion and large motions. In stark contrast to flow-based methods, we formulate HDR imaging as an image translation problem without optical flows. Moreover, our simple translation network can automatically hallucinate plausible HDR details in the presence of total occlusion, saturation and under-exposure, which are otherwise almost impossible to recover by conventional optimization approaches. Our framework can also be extended for different reference images. We performed extensive qualitative and quantitative comparisons to show that our approach produces excellent results where color artifacts and geometric distortions are significantly reduced compared to existing state-of-the-art methods, and is robust across various inputs, including images without radiometric calibration.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/bf4619cf559c921ac0f3a393e1ddf78a9262e9cb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Generative Diffusion Prior for Unified Image Restoration and Enhancement (2023, methodology): “Moreover, we also show more samples compared with the state-of-the-art methods, including AHDRNet [91], HDR-GAN [59], DeepHDR [90] and deep-high-dynamicrange [30].”
EnlightenGAN: Deep Light Enhancement Without Paired Supervision (2019, methodology): “In the high-dynamic-ranging (HDR) field, a few works first capture several images at different imperfect light conditions, then align and fuse them into one high-quality image [15, 17].”
Attention-Guided Network for Ghost-Free High Dynamic Range Imaging (2019, methodology): “Previous methods [15, 37] take stacked LDR images, or LDR image feature maps, as the input to the merging process, which mixes the misaligned image components at an early stage of the network, making it difficult to obtain ghost-free HDR results.”
FastDVDnet: Towards Real-Time Deep Video Denoising Without Flow Estimation (2019, background): “Multi-scale, U-Net-like architectures have been shown to have the ability to learn misalignment [50, 15].”