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

2026-08-16

AI Summary

This study addresses the challenges of single-shot HDR imaging for robotics under extreme lighting conditions and the absence of standardized evaluation benchmarks. We propose Depth-Guided Multi-View Exposure Bracketing (DMEB), a novel paradigm that achieves robust perception through differentiated multi-camera exposures and depth-confidence-weighted fusion. Furthermore, we construct a large-scale real-synthetic hybrid dataset leveraging CARLA simulation. As the first comprehensive benchmark for robotic HDR perception, DMEB establishes strong reference baselines on this newly created dataset. Our approach effectively validates the HDR sensing capabilities of multi-camera depth systems in complex environments, thereby bridging critical gaps in both data availability and evaluation standards within this domain.

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.

Problem

• HDR imaging
• robot vision
• benchmark dataset
• extreme illumination
• multi-sensor system

Innovation

• Depth-guided Multi-view Exposure Bracketing
• Single-shot HDR
• Confidence-aware Fusion
• Robotic Vision Benchmark
• Multi-sensor Fusion