Towards Geometry Guided Neural Relighting with Flash Photography
This work addresses the challenge of simplifying data capture for image relighting, which is useful for applications like mobile photography, though it is incremental as it builds on existing deep learning approaches by incorporating geometric information.
The paper tackles the problem of image relighting by proposing a framework that uses a single flash photograph and its depth map to generate realistic high-frequency lighting effects, such as glossy highlights and cast shadows, under novel lighting conditions, achieving improved performance over state-of-the-art methods in intrinsic image decomposition and relighting.
Previous image based relighting methods require capturing multiple images to acquire high frequency lighting effect under different lighting conditions, which needs nontrivial effort and may be unrealistic in certain practical use scenarios. While such approaches rely entirely on cleverly sampling the color images under different lighting conditions, little has been done to utilize geometric information that crucially influences the high-frequency features in the images, such as glossy highlight and cast shadow. We therefore propose a framework for image relighting from a single flash photograph with its corresponding depth map using deep learning. By incorporating the depth map, our approach is able to extrapolate realistic high-frequency effects under novel lighting via geometry guided image decomposition from the flashlight image, and predict the cast shadow map from the shadow-encoding transformed depth map. Moreover, the single-image based setup greatly simplifies the data capture process. We experimentally validate the advantage of our geometry guided approach over state-of-the-art image-based approaches in intrinsic image decomposition and image relighting, and also demonstrate our performance on real mobile phone photo examples.