UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes
–Neural Information Processing Systems
Such conditions are commonly encountered in nighttime scenes with light sources. Even with standard exposure settings, a bimodal intensity distribution with boundary peaks often emerges, making it difficult to preserve both highlight and shadow details simultaneously. RGB-based bracketing methods can capture details at both ends using short-long exposure pairs, but are susceptible to misalignment and ghosting artifacts. We found that a shortexposure image already retains sufficient highlight detail. The main challenge of UHDR reconstruction lies in denoising and recovering information in dark regions.
Neural Information Processing Systems
Jun-16-2026, 13:12:24 GMT
- Genre:
- Research Report
- New Finding (1.00)
- Experimental Study (1.00)
- Research Report
- Industry:
- Media > Photography (0.90)
- Technology:
- Information Technology
- Sensing and Signal Processing > Image Processing (1.00)
- Communications (0.68)
- Artificial Intelligence
- Vision (1.00)
- Machine Learning > Neural Networks (1.00)
- Natural Language (0.68)
- Representation & Reasoning (0.67)
- Information Technology