# Recurrent Dynamic Range Extension

arXiv: https://arxiv.org/abs/2609.13135 · HTML: https://mlsanity.com/paper/2609.13135/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 64 references that are in the map.
- First posted on arXiv 11 Sep 2026.

## Builds on (most cited first, 30 of 32)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer](https://mlsanity.com/paper/1907.01341/) (2019)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [HDR image reconstruction from a single exposure using deep CNNs](https://mlsanity.com/paper/1710.07480/) (2017)
- [Learning to Predict Indoor Illumination from a Single Image](https://mlsanity.com/paper/1704.00090/) (2017)
- [Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline](https://mlsanity.com/paper/2004.01179/) (2020)
- [Learning Monocular Dense Depth from Events](https://mlsanity.com/paper/2010.08350/) (2020)
- [Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Loss](https://mlsanity.com/paper/2005.07335/) (2020)
- [Memformer: A Memory-Augmented Transformer for Sequence Modeling](https://mlsanity.com/paper/2010.06891/) (2020)
- [PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency](https://mlsanity.com/paper/2105.09180/) (2021)
- [The GAN is dead; long live the GAN! A Modern GAN Baseline](https://mlsanity.com/paper/2501.05441/) (2025)
- [HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular content](https://mlsanity.com/paper/2304.13625/) (2023)
- [ColorVideoVDP: A visual difference predictor for image, video and display distortions](https://mlsanity.com/paper/2401.11485/) (2024)
- [RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image](https://mlsanity.com/paper/2309.02020/) (2023)
- [Deep Chain HDRI: Reconstructing a High Dynamic Range Image from a Single Low Dynamic Range Image](https://mlsanity.com/paper/1801.06277/) (2018)
- [LEDiff: Latent Exposure Diffusion for HDR Generation](https://mlsanity.com/paper/2412.14456/) (2024)
- [Single-Image HDR Reconstruction by Multi-Exposure Generation](https://mlsanity.com/paper/2210.15897/) (2022)
- [Luminance Attentive Networks for HDR Image and Panorama Reconstruction](https://mlsanity.com/paper/2109.06688/) (2021)
- [End-to-End Differentiable Learning to HDR Image Synthesis for Multi-exposure Images](https://mlsanity.com/paper/2006.15833/) (2020)
- [Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising](https://mlsanity.com/paper/2405.14304/) (2024)
- [Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Prediction](https://mlsanity.com/paper/2304.12372/) (2023)
- [GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDR](https://mlsanity.com/paper/2504.10809/) (2025)
- [Few-Shot Domain Adaptation for Low Light RAW Image Enhancement](https://mlsanity.com/paper/2303.15528/) (2023)
- [LHDR: HDR Reconstruction for Legacy Content using a Lightweight DNN](https://mlsanity.com/paper/2211.11270/) (2022)
- [Deep HDR Hallucination for Inverse Tone Mapping](https://mlsanity.com/paper/2106.09486/) (2021)

## Abstract (arXiv)

We present an approach to progressively extend the highlights of an image. Instead of reconstructing the full dynamic range of a complex scene directly, we learn a simpler task first: We extend the dynamic range of an input image by a single exposure value. Once this is mastered, we retrieve the full HDR image for the scene by executing our network recurrently, progressively increasing the dynamic range of the input. Our formulation is agnostic to the input dynamic range and targets a bounded output domain. This enables us to use widely available RAW images for the reconstruction task and adapt adversarial losses to construct realistic images. By incorporating Memory Replay for backpropagation, we can train our network recurrently over multiple inference stages and reduce reconstruction errors. As a consequence, our system reconstructs challenging long-tailed HDR scenes robustly and shows powerful recovery of bright light sources and highlights.