High-Speed Full-Color HDR Imaging via Unwrapping Modulo-Encoded Spike Streams
Not on the map. Why?
Abstract (arXiv)
Conventional RGB-based high dynamic range (HDR) imaging faces a fundamental trade-off between motion artifacts in multi-exposure captures and irreversible information loss in single-shot techniques. Modulo sensors offer a promising alternative by encoding theoretically unbounded dynamic range into wrapped measurements. However, existing modulo solutions remain bottlenecked by iterative unwrapping overhead and hardware constraints limiting them to low-speed, grayscale capture. In this work, we present a complete modulo-based HDR imaging system that enables high-speed, full-color HDR acquisition by synergistically advancing both the sensing formulation and the unwrapping algorithm. At the core of our approach is an exposure-decoupled formulation of modulo imaging that allows multiple measurements to be interleaved in time, preserving a clean, observation-wise measurement model. Building upon this, we introduce an iteration-free unwrapping algorithm that integrates diffusion-based generative priors with the physical least absolute remainder property of modulo images, supporting highly efficient, physics-consistent HDR reconstruction. Finally, to validate the practical viability of our system, we demonstrate a proof-of-concept hardware implementation based on modulo-encoded spike streams. This setup preserves the native high temporal resolution of spike cameras, achieving 1000 FPS full-color imaging while reducing output data bandwidth from approximately 20 Gbps to 6 Gbps. Extensive evaluations indicate that our coordinated approach successfully overcomes key systemic bottlenecks, demonstrating the feasibility of deploying modulo imaging in dynamic scenarios.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 64 references that are in the map. First posted on arXiv 16 Apr 2026.
Builds on
27 of 64 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
- 2020Denoising Diffusion Implicit Modelscited by 9,781
- 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2018CBAM: Convolutional Block Attention Modulecited by 2,477
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
- 2019High Speed and High Dynamic Range Video with an Event Cameracited by 345
- 2017HDR image reconstruction from a single exposure using deep CNNscited by 167
- 2020Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipelinecited by 132
15 more
- 2021Benchmarking Detection Transfer Learning with Vision Transformerscited by 131
- 2018ExpandNet: A Deep Convolutional Neural Network for High Dynamic Range Expansion from Low Dynamic Range Contentcited by 89
- 2020HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motionscited by 80
- 2020Single Image HDR Reconstruction Using a CNN with Masked Features and Perceptual Losscited by 71
- 2019Deep Optics for Single-shot High-dynamic-range Imagingcited by 62
- 2023HDR-VDP-3: A multi-metric for predicting image differences, quality and contrast distortions in high dynamic range and regular contentcited by 41
- 2019A Retina-inspired Sampling Method for Visual Texture Reconstructioncited by 34
- 2024HDRFlow: Real-Time HDR Video Reconstruction with Large Motionscited by 31
- 2020An Asynchronous Kalman Filter for Hybrid Event Camerascited by 26
- 2024LEDiff: Latent Exposure Diffusion for HDR Generationcited by 22
- 2025UltraFusion: Ultra High Dynamic Imaging using Exposure Fusioncited by 21
- 2018Convolutional Sparse Coding for High Dynamic Range Imagingcited by 17
- 2024Generating Content for HDR Deghosting from Frequency Viewcited by 14
- 2025AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigmcited by 13
- 2024Intrinsic Single-Image HDR Reconstructioncited by 11
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Autoregressive High-Order Finite Difference Modulo Imaging: High-Dynamic Range for Computer Vision Applications
- 2026Single-Shot HDR Recovery via a Video Diffusion Prior
- 2023HDR Imaging With One-Bit Quantization
- 2024Event-assisted 12-stop HDR Imaging of Dynamic Scene
- 2026Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping
- 2026ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
- 2026X2HDR: HDR Image Generation in a Perceptually Uniform Space
- 2025AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes