mlsanityData to 14 Oct 2026

Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision

arXiv 2608.16014 ↗First posted 17 Aug 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Achieving reliable single-shot high dynamic range (HDR) imaging under extreme illumination conditions remains a long-standing challenge, yet no comprehensive benchmark exist for evaluating HDR perception in multi-sensor robotic systems. To fill this gap, we introduce a large-scale dataset collected via a custom robotic vision platform and an iPhone 13 Pro: 121 real-world scenes spanning modest and ultra-high dynamic range conditions, alongside 20 synthetic video sequences from the CARLA simulator. As a reference pipeline for this dataset, we propose Depth-guided Multi-view Exposure Bracketing (DMEB), a single-shot HDR method that distributes drastically different exposures across multi-view low-bit-depth cameras and fuses them via depth-guided confidence-aware fusion. Evaluations on our dataset show that DMEB establishes a strong reference point and highlight the promise of this sensor configuration for robust HDR perception in diverse multi-camera and depth sensor system.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 52 references that are in the map. First posted on arXiv 17 Aug 2026.

Builds on

20 of 52 references.

References · 20

  1. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  2. 2024Depth Anything V2cited by 1,422
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  4. 20223D Object Detection for Autonomous Driving: A Comprehensive Surveycited by 132
  5. 2019Attention-guided Network for Ghost-free High Dynamic Range Imagingcited by 117
  6. 2022Ghost-free High Dynamic Range Imaging with Context-aware Transformercited by 65
  7. 2019Deep Optics for Single-shot High-dynamic-range Imagingcited by 62
  8. 2021HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Datasetcited by 45
  9. 2023RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Imagecited by 32
  10. 2024HDRFlow: Real-Time HDR Video Reconstruction with Large Motionscited by 31
  11. 2024LetsGo: Large-Scale Garage Modeling and Rendering via LiDAR-Assisted Gaussian Primitivescited by 26
  12. 2024SAFNet: Selective Alignment Fusion Network for Efficient HDR Imagingcited by 23
8 more
  1. 2013A Unified Framework for Multi-Sensor HDR Video Reconstructioncited by 20
  2. 2022FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imagingcited by 17
  3. 2023A Unified HDR Imaging Method with Pixel and Patch Levelcited by 17
  4. 2024Towards Real-World HDR Video Reconstruction: A Large-Scale Benchmark Dataset and A Two-Stage Alignment Networkcited by 14
  5. 2025AFUNet: Cross-Iterative Alignment-Fusion Synergy for HDR Reconstruction via Deep Unfolding Paradigmcited by 13
  6. 2025Capturing Stable HDR Videos Using a Dual-Camera Systemcited by 3
  7. 2025Region-aware Depth Scale Adaptation with Sparse Measurementscited by 3
  8. 2024Dual Exposure Stereo for Extended Dynamic Range 3D Imagingcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025AdaptiveAE: An Adaptive Exposure Strategy for HDR Capturing in Dynamic Scenes
  2. 2024Event-assisted 12-stop HDR Imaging of Dynamic Scene
  3. 2026Single-Shot HDR Recovery via a Video Diffusion Prior
  4. 2022HDR Reconstruction from Bracketed Exposures and Events
  5. 2026Dual-Output Multi-Exposure HDR Reconstruction via SDR Fusion and Gain Map Inverse Tone Mapping
  6. 2021A New Comprehensive Framework for Multi-Exposure Stereo Coding Utilizing Low Rank Tucker-ALS and 3D-HEVC Techniques
  7. 2026ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
  8. 2024D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation