mlsanityData to 14 Oct 2026

Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction

arXiv 2309.03900 ↗First posted 7 Sep 2023eess.IV cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Deep learning is commonly used to reconstruct HDR images from LDR images. LDR stack-based methods are used for single-image HDR reconstruction, generating an HDR image from a deep learning-generated LDR stack. However, current methods generate the stack with predetermined exposure values (EVs), which may limit the quality of HDR reconstruction. To address this, we propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training. Our approach generates a continuous stack with more images containing diverse EVs, significantly improving HDR reconstruction. We use a cycle training strategy to supervise the model in generating continuous EV LDR images without corresponding ground truths. Our CEVR model outperforms existing methods, as demonstrated by experimental results.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 37 of its 69 references that are in the map. First posted on arXiv 7 Sep 2023.

Builds on

37 of 69 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  6. 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
  7. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  9. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  10. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  11. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  12. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
25 more
  1. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  2. 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 700
  3. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  4. 2018Generative Image Inpainting with Contextual Attentioncited by 580
  5. 2020Learning Continuous Image Representation with Local Implicit Image Functioncited by 552
  6. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  7. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505
  8. 2019SAL: Sign Agnostic Learning of Shapes from Raw Datacited by 390
  9. 2020Implicit Functions in Feature Space for 3D Shape Reconstruction and Completioncited by 343
  10. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  11. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
  12. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 132
  13. 2021Local Texture Estimator for Implicit Representation Functioncited by 127
  14. 2023Progressively Optimized Local Radiance Fields for Robust View Synthesiscited by 103
  15. 2017Deep High Dynamic Range Imaging with Large Foreground Motionscited by 99
  16. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  17. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  18. 2022CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Trainingcited by 49
  19. 2022Denoising Likelihood Score Matching for Conditional Score-based Data Generationcited by 46
  20. 2017Learning High Dynamic Range from Outdoor Panoramascited by 34
  21. 2018Image Correction via Deep Reciprocating HDR Transformationcited by 30
  22. 2018Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Imagecited by 25
  23. 2021Hybrid Neural Fusion for Full-frame Video Stabilizationcited by 21
  24. 2018Convolutional Sparse Coding for High Dynamic Range Imagingcited by 17
  25. 2020End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Imagescited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 4.

11 papers.

  1. 2024Bracket Diffusion: HDR Image Generation by Consistent LDR Denoisingcited by 15
  2. 2024Video Quality Assessment: A Comprehensive Surveycited by 15
  3. 2025NTIRE 2025 Challenge on Efficient Burst HDR and Restoration: Datasets, Methods, and Resultscited by 14
  4. 2024Intrinsic Single-Image HDR Reconstructioncited by 11
  5. 2024Anything in Any Scene: Photorealistic Video Object Insertioncited by 9
  6. 2025Generative Refocusing: Flexible Defocus Control from a Single Imagecited by 4
  7. 2026RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenescited by 2
  8. 2025UNICE: Training A Universal Image Contrast Enhancercited by 0
  9. 2026HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusioncited by 0
  10. 2026High Dynamic Range Video Reconstruction from Single-Exposure Raw Sequencescited by 0
  11. 2026HaRP: High Dynamic Range Photosequencing through Dual Reversed Shutter Scanningcited by 0