Image system improves bright highlights by extending dynamic range gradually
Recurrent Dynamic Range Extension
Computer Vision and Pattern RecognitionGraphics
Summary
Capturing very bright parts of a scene well is hard with normal cameras. The authors created a method that improves images step-by-step by brightening them a little at a time. Their system learns how to enhance images gradually and can be run multiple times to reveal details in extremely bright areas. This approach works with common RAW photos and produces realistic results even in difficult lighting. They also made the training smarter by remembering past improvements to reduce mistakes.
What this means in practice
- •For photography software developers: Enhance photo editing tools to reveal bright details progressively in HDR images from RAW inputs.
- •For mobile camera app developers: Implement progressive dynamic range enhancement to improve smartphone photos taken under challenging lighting.$Commercial implications: Allows selling camera apps that produce superior HDR photos on common devices by gradual brightening techniques.
Authors
Sebastian Dille, Keru Fu, S. Mahdi H. Miangoleh, Yağız Aksoy
Abstract
We present an approach to progressively extend the highlights of an image. Instead of reconstructing the full dynamic range of a complex scene directly, we learn a simpler task first: We extend the dynamic range of an input image by a single exposure value. Once this is mastered, we retrieve the full HDR image for the scene by executing our network recurrently, progressively increasing the dynamic range of the input. Our formulation is agnostic to the input dynamic range and targets a bounded output domain. This enables us to use widely available RAW images for the reconstruction task and adapt adversarial losses to construct realistic images. By incorporating Memory Replay for backpropagation, we can train our network recurrently over multiple inference stages and reduce reconstruction errors. As a consequence, our system reconstructs challenging long-tailed HDR scenes robustly and shows powerful recovery of bright light sources and highlights.