Research Information System
IEEE Transactions on Image Processing, vol.33, pp.6592-6606, 2024 (SCI-Expanded)
The increased interest in consumer-grade high dynamic range (HDR) images and videos in recent years has caused a proliferation of HDR deghosting algorithms. Despite numerous proposals, a fast, memory-efficient, and robust algorithm has been difficult to achieve. This paper addresses this problem by leveraging the power of attention and U-Net-based neural representations and using a conservative deghosting strategy. Given two bracketed exposures of a scene, we produce an HDR image that maximally resembles the high exposure where it is well-exposed and fuses aligned information from both exposures otherwise. We evaluate the performance of our algorithm under several different challenging scenarios, using both visual and quantitative results, and show that it matches the state-of-the-art algorithms despite using only two exposures and having significantly lower computational complexity. Furthermore, the parameters of our algorithm greatly simplify deploying its different versions for devices with a variety of computational constraints, including mobile devices.