# Boosting HDR Image Reconstruction via Semantic Knowledge Transfer

arXiv: https://arxiv.org/abs/2503.15361 · HTML: https://mlsanity.com/paper/2503.15361/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 34 of its 66 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 34)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019)
- [Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform](https://mlsanity.com/paper/1804.02815/) (2018)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [Attention-guided Network for Ghost-free High Dynamic Range Imaging](https://mlsanity.com/paper/1904.10293/) (2019)
- [Blind Face Restoration via Deep Multi-scale Component Dictionaries](https://mlsanity.com/paper/2008.00418/) (2020)
- [HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions](https://mlsanity.com/paper/2007.01628/) (2020)
- [Ghost-free High Dynamic Range Imaging with Context-aware Transformer](https://mlsanity.com/paper/2208.05114/) (2022)
- [Burst Image Restoration and Enhancement](https://mlsanity.com/paper/2110.03680/) (2021)
- [Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement](https://mlsanity.com/paper/2110.00970/) (2021)
- [Learning Semantic-Aware Knowledge Guidance for Low-Light Image Enhancement](https://mlsanity.com/paper/2304.07039/) (2023)
- [Deep Learning for HDR Imaging: State-of-the-Art and Future Trends](https://mlsanity.com/paper/2110.10394/) (2021)
- [When Image Denoising Meets High-Level Vision Tasks: A Deep Learning Approach](https://mlsanity.com/paper/1706.04284/) (2017)
- [Towards High-quality HDR Deghosting with Conditional Diffusion Models](https://mlsanity.com/paper/2311.00932/) (2023)
- [Burstormer: Burst Image Restoration and Enhancement Transformer](https://mlsanity.com/paper/2304.01194/) (2023)
- [Alignment-free HDR Deghosting with Semantics Consistent Transformer](https://mlsanity.com/paper/2305.18135/) (2023)
- [RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image](https://mlsanity.com/paper/2309.02020/) (2023)
- [Semantically Contrastive Learning for Low-light Image Enhancement](https://mlsanity.com/paper/2112.06451/) (2021)
- [HDRFlow: Real-Time HDR Video Reconstruction with Large Motions](https://mlsanity.com/paper/2403.03447/) (2024)
- [Distilling Semantic Priors from SAM to Efficient Image Restoration Models](https://mlsanity.com/paper/2403.16368/) (2024)
- [Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration](https://mlsanity.com/paper/2107.06211/) (2021)
- [SAFNet: Selective Alignment Fusion Network for Efficient HDR Imaging](https://mlsanity.com/paper/2407.16308/) (2024)
- [FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging](https://mlsanity.com/paper/2201.02625/) (2022)
- [A Unified HDR Imaging Method with Pixel and Patch Level](https://mlsanity.com/paper/2304.06943/) (2023)
- [UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data](https://mlsanity.com/paper/2102.01850/) (2021)
- [Generating Content for HDR Deghosting from Frequency View](https://mlsanity.com/paper/2404.00849/) (2024)

## Built on by (most cited first, 2 of 2)

- [Chain-of-Evidence Multimodal Reasoning for Few-shot Temporal Action Localization](https://mlsanity.com/paper/2504.13460/) (2025)
- [GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction](https://mlsanity.com/paper/2512.16357/) (2025)

## Abstract (arXiv)

Recovering High Dynamic Range (HDR) images from multiple Standard Dynamic Range (SDR) images become challenging when the SDR images exhibit noticeable degradation and missing content. Leveraging scene-specific semantic priors offers a promising solution for restoring heavily degraded regions. However, these priors are typically extracted from sRGB SDR images, the domain/format gap poses a significant challenge when applying it to HDR imaging. To address this issue, we propose a general framework that transfers semantic knowledge derived from SDR domain via self-distillation to boost existing HDR reconstruction. Specifically, the proposed framework first introduces the Semantic Priors Guided Reconstruction Model (SPGRM), which leverages SDR image semantic knowledge to address ill-posed problems in the initial HDR reconstruction results. Subsequently, we leverage a self-distillation mechanism that constrains the color and content information with semantic knowledge, aligning the external outputs between the baseline and SPGRM. Furthermore, to transfer the semantic knowledge of the internal features, we utilize a Semantic Knowledge Alignment Module (SKAM) to fill the missing semantic contents with the complementary masks. Extensive experiments demonstrate that our framework significantly boosts HDR imaging quality for existing methods without altering the network architecture.