Robust Reflection Removal with Reflection-free Flash-only Cues
This addresses the issue of unwanted reflections in photography for applications like computer vision and image processing, representing an incremental advance with a novel method for a known bottleneck.
The paper tackles the problem of reflection removal from images by using a flash-only image derived from flash and ambient image pairs, achieving state-of-the-art performance with improvements of over 5.23dB in PSNR, 0.04 in SSIM, and 0.068 in LPIPS.
We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. We observe that this flash-only image is visually reflection-free, and thus it can provide robust cues to infer the reflection in the ambient image. Since the flash-only image usually has artifacts, we further propose a dedicated model that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate reflection and transmission. Our experiments on real-world images with various types of reflection demonstrate the effectiveness of our model with reflection-free flash-only cues: our model outperforms state-of-the-art reflection removal approaches by more than 5.23dB in PSNR, 0.04 in SSIM, and 0.068 in LPIPS. Our source code and dataset are publicly available at {github.com/ChenyangLEI/flash-reflection-removal}.