Depth-guided Multi-view Exposure Bracketing for HDR Robot Vision
2026-08-17 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the difficulty of capturing clear images in scenes with very bright and very dark areas using multiple cameras and sensors. They created a large dataset with real and simulated scenes to help test and improve these techniques. They also developed a new method called DMEB, which uses different camera exposures and depth information to combine images into one clear, high-quality picture. Their tests show that DMEB works well and their dataset can help future research on multi-camera systems for tough lighting conditions.
High Dynamic Range (HDR)Multi-sensor SystemsExposure BracketingDepth-guided FusionRobotic VisionMulti-view ImagingDatasetImage FusionSynthetic DataCARLA Simulator
Authors
Jinnyeong Kim, Juhyung Choi, Woohyeok Kim, Sunghyun Cho, Seung-Hwan Baek
Abstract
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.