Guided Co-Modulated GAN for 360° Field of View Extrapolation
This addresses the need for controlled panoramic image generation, with applications like virtual object insertion, but is incremental as it builds on an existing GAN-based architecture.
The paper tackles the problem of extrapolating a 360° field of view from a single image with user-controlled synthesis, achieving state-of-the-art results on standard image quality metrics.
We propose a method to extrapolate a 360° field of view from a single image that allows for user-controlled synthesis of the out-painted content. To do so, we propose improvements to an existing GAN-based in-painting architecture for out-painting panoramic image representation. Our method obtains state-of-the-art results and outperforms previous methods on standard image quality metrics. To allow controlled synthesis of out-painting, we introduce a novel guided co-modulation framework, which drives the image generation process with a common pretrained discriminative model. Doing so maintains the high visual quality of generated panoramas while enabling user-controlled semantic content in the extrapolated field of view. We demonstrate the state-of-the-art results of our method on field of view extrapolation both qualitatively and quantitatively, providing thorough analysis of our novel editing capabilities. Finally, we demonstrate that our approach benefits the photorealistic virtual insertion of highly glossy objects in photographs.