DSRN: an Efficient Deep Network for Image Relighting
This work addresses the need for faster and more memory-efficient image relighting tools for photo editing applications, though it is incremental in improving existing multi-scale models.
The paper tackles the problem of inefficient and memory-intensive deep learning methods for image relighting by proposing DSRN, an efficient real-time framework that achieves an average inference time of 0.0116s for 1024x1024 images with a model size of 42 MB.
Custom and natural lighting conditions can be emulated in images of the scene during post-editing. Extraordinary capabilities of the deep learning framework can be utilized for such purpose. Deep image relighting allows automatic photo enhancement by illumination-specific retouching. Most of the state-of-the-art methods for relighting are run-time intensive and memory inefficient. In this paper, we propose an efficient, real-time framework Deep Stacked Relighting Network (DSRN) for image relighting by utilizing the aggregated features from input image at different scales. Our model is very lightweight with total size of about 42 MB and has an average inference time of about 0.0116s for image of resolution $1024 \times 1024$ which is faster as compared to other multi-scale models. Our solution is quite robust for translating image color temperature from input image to target image and also performs moderately for light gradient generation with respect to the target image. Additionally, we show that if images illuminated from opposite directions are used as input, the qualitative results improve over using a single input image.