mlsanityData to 7 Oct 2026

ISETHDR: A Physics-based Synthetic Radiance Dataset for High Dynamic Range Driving Scenes

arXiv 2408.12048 ↗First posted 22 Aug 2024cs.CV eess.IVcited by 1

Not on the map. Why?

Abstract (arXiv)

This paper describes a physics-based end-to-end software simulation for image systems. We use the software to explore sensors designed to enhance performance in high dynamic range (HDR) environments, such as driving through daytime tunnels and under nighttime conditions. We synthesize physically realistic HDR spectral radiance images and use them as the input to digital twins that model the optics and sensors of different systems. This paper makes three main contributions: (a) We create a labeled (instance segmentation and depth), synthetic radiance dataset of HDR driving scenes. (b) We describe the development and validation of the end-to-end simulation framework. (c) We present a comparative analysis of two single-shot sensors designed for HDR. We open-source both the dataset and the software.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 52 references that are in the map. First posted on arXiv 22 Aug 2024.

Builds on

20 of 52 references.

References · 20

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,618
  3. 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
  4. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  5. 2018Dark Model Adaptation: Semantic Image Segmentation from Daytime to Nighttimecited by 122
  6. 2020Map-Guided Curriculum Domain Adaptation and Uncertainty-Aware Evaluation for Semantic Nighttime Image Segmentationcited by 86
  7. 2020How to Train Neural Networks for Flare Removalcited by 50
  8. 2022Flare7K: A Phenomenological Nighttime Flare Removal Datasetcited by 49
  9. 2023Flare7K++: Mixing Synthetic and Real Datasets for Nighttime Flare Removal and Beyondcited by 31
  10. 2019See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversioncited by 30
  11. 2022Day-to-Night Image Synthesis for Training Nighttime Neural ISPscited by 23
  12. 2023Improving Lens Flare Removal with General Purpose Pipeline and Multiple Light Sources Recoverycited by 21
8 more
  1. 2019Neural Network Generalization: The impact of camera parameterscited by 14
  2. 2016Learning the image processing pipelinecited by 9
  3. 2019Soft Prototyping Camera Designs for Car Detection Based on a Convolutional Neural Networkcited by 7
  4. 2019IMMVP: An Efficient Daytime and Nighttime On-Road Object Detectorcited by 4
  5. 2021ISETAuto: Detecting vehicles with depth and radiance informationcited by 3
  6. 2024Gated Fields: Learning Scene Reconstruction from Gated Videoscited by 3
  7. 2021Validation of image systems simulation technology using a Cornell Boxcited by 1
  8. 2022Ray-transfer functions for camera simulation of 3D scenes with hidden lens designcited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024A Cycle Ride to HDR: Semantics Aware Self-Supervised Framework for Unpaired LDR-to-HDR Image Reconstructioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025PhysHDR: When Lighting Meets Materials and Scene Geometry in HDR Reconstruction
  2. 2025Industrial-Grade Sensor Simulation via Gaussian Splatting: A Modular Framework for Scalable Editing and Full-Stack Validation
  3. 2023NeuRAD: Neural Rendering for Autonomous Driving
  4. 2025ThermalDiffusion: Visual-to-Thermal Image-to-Image Translation for Autonomous Navigation
  5. 2025Solar Altitude Guided Scene Illumination
  6. 2026Real2Sim: A Physics-driven and Editable Gaussian Splatting Framework for Autonomous Driving Scenes
  7. 2026Video Generation Models Are Inherent Lighting Estimators
  8. 2026ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction