mlsanityData to 13 Oct 2026

ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR Reconstruction

arXiv 2609.39624 ↗First posted 30 Sep 2026cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic range and exposure cause LDR images to lose varying amounts of information in shadows and highlights. We present ExpandDiff, a conditional diffusion pipeline that jointly reconstructs clipped shadows and highlights. To account for this variation, we introduce Dynamic Clipping Synthesis (DCS), which randomly samples shadow and highlight clipping percentiles when constructing training inputs from HDR targets. A pixel-space diffusion model guided by spatially-adaptive normalization then predicts perceptually encoded HDR through a bounded output head, reconstructing both clipping directions in one sampling trajectory. On the SI-HDR benchmark, ExpandDiff variants improve HDR reconstruction accuracy by 3.43 dB in PU21-PSNR over the strongest evaluated competing method, and by 7.34 dB under two-sided clipping. The code and supplementary material are available at https://memreandiran.github.io/expanddiff/.

Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 16 of its 24 references that are in the map. First posted on arXiv 30 Sep 2026.

Builds on

16 of 24 references.

References · 16

  1. 2020Denoising Diffusion Implicit Modelscited by 9,718
  2. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,549
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,296
  4. 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
  5. 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 131
  6. 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
  7. 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
  8. 2023HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular contentcited by 41
  9. 2024LEDiff: Latent Exposure Diffusion for HDR Generationcited by 22
  10. 2023Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Predictioncited by 14
  11. 2023Single Image LDR to HDR Conversion using Conditional Diffusioncited by 9
  12. 2024RAW-Diffusion: RGB-Guided Diffusion Models for High-Fidelity RAW Image Generationcited by 8
4 more
  1. 2025AIM 2025 challenge on Inverse Tone Mapping Report: Methods and Resultscited by 8
  2. 2024Semantic Aware Diffusion Inverse Tone Mappingcited by 7
  3. 2026X2HDR: HDR Image Generation in a Perceptually Uniform Spacecited by 7
  4. 2026ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstructioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion
  2. 2024Diffusion-Promoted HDR Video Reconstruction
  3. 2025GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction
  4. 2026Single-Shot HDR Recovery via a Video Diffusion Prior
  5. 2026DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models
  6. 2024Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
  7. 2024Generating Content for HDR Deghosting from Frequency View
  8. 2025PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction