Removing Reflections from RAW Photos

TL;DR

This paper presents a novel system for removing reflections from RAW photos using synthetic training data, optional contextual images, and a two-stage neural network, achieving state-of-the-art results efficiently.

Contribution

The authors introduce a reflection removal system trained solely on synthetic RAW data, utilizing an optional context photo for disambiguation, and demonstrate superior performance over prior methods.

Findings

Achieves state-of-the-art reflection removal on real RAW photos.

Training on synthetic data improves performance more than architectural changes.

Operates efficiently at 256p with fast up-sampling to full resolution.

Abstract

We describe a system to remove real-world reflections from images for consumer photography. Our system operates on linear (RAW) photos, and accepts an optional contextual photo looking in the opposite direction (e.g., the "selfie" camera on a mobile device). This optional photo disambiguates what should be considered the reflection. The system is trained solely on synthetic mixtures of real RAW photos, which we combine using a reflection simulation that is photometrically and geometrically accurate. Our system comprises a base model that accepts the captured photo and optional context photo as input, and runs at 256p, followed by an up-sampling model that transforms 256p images to full resolution. The system produces preview images at 1K in 4.5-6.5s on a MacBook or iPhone 14 Pro. We show SOTA results on RAW photos that were captured in the field to embody typical consumer photos, and show that training on RAW simulation data improves performance more than the architectural variations among prior works.