HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization

2021/05/27 by Xiangyu Chen, Chen, Xiangyu, Yihao Liu +7 · 7 citations
Computer Science · Engineering · #Advanced Image Processing Techniques #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Dynamic range #FOS: Computer and information sciences #FOS: Electrical engineering #High dynamic range #Image Enhancement Techniques #Image and Signal Denoising Methods #Image and Video Processing (eess.IV) #Noise reduction #Preprocessor #Quantization (signal processing) #Tone mapping #Weighting #cs.CV #eess.IV #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2105.13084

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2021/05/27 · openalex created_date 2021/06/07 · arxiv created 2021/06/19 · arxiv updated 2021/06/22 · openalex updated_date 2026/08/06

Abstract

Most consumer-grade digital cameras can only capture a limited range of luminance in real-world scenes due to sensor constraints. Besides, noise and quantization errors are often introduced in the imaging process. In order to obtain high dynamic range (HDR) images with excellent visual quality, the most common solution is to combine multiple images with different exposures. However, it is not always feasible to obtain multiple images of the same scene and most HDR reconstruction methods ignore the noise and quantization loss. In this work, we propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction with denoising and dequantization. The network consists of a UNet-style base network to make full use of the hierarchical multi-scale information, a condition network to perform pattern-specific modulation and a weighting network for selectively retaining information. Moreover, we propose a Tanh_L1 loss function to balance the impact of over-exposed values and well-exposed values on the network learning. Our method achieves the state-of-the-art performance in quantitative comparisons and visual quality. The proposed HDRUNet model won the second place in the single frame track of NITRE2021 High Dynamic Range Challenge.

Citations

• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising

Cited by

• Enabling High-Quality In-the-Wild Imaging from Severely Aberrated Metalens Bursts
• Lightweight and Fast Real-time Image Enhancement via Decomposition of the Spatial-aware Lookup Tables
• Exploring Scalable Unified Modeling for General Low-Level Vision
• UNICE: Training A Universal Image Contrast Enhancer
• Mask6D: Masked Pose Priors For 6D Object Pose Estimation
• Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping
• Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision

Related

• Single-Image HDR Reconstruction by Multi-Exposure Generation
• Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
• End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Images
• A Two-stage Deep Network for High Dynamic Range Image Reconstruction
• Hybrid Loss for Learning Single-Image-based HDR Reconstruction