2S-ODIS: Two-Stage Omni-Directional Image Synthesis by Geometric Distortion Correction

TL;DR

This paper introduces 2S-ODIS, a two-stage method for omni-directional image synthesis that leverages pre-trained VQGAN to produce high-quality images with significantly reduced training time.

Contribution

The paper proposes a novel two-stage synthesis approach using pre-trained VQGAN, enabling efficient and high-quality omni-directional image generation without extensive training.

Findings

Reduced training time from 14 days to 4 days

Achieved high-quality omni-directional images

Utilized pre-trained VQGAN without fine-tuning

Abstract

Omni-directional images have been increasingly used in various applications, including virtual reality and SNS (Social Networking Services). However, their availability is comparatively limited in contrast to normal field of view (NFoV) images, since specialized cameras are required to take omni-directional images. Consequently, several methods have been proposed based on generative adversarial networks (GAN) to synthesize omni-directional images, but these approaches have shown difficulties in training of the models, due to instability and/or significant time consumption in the training. To address these problems, this paper proposes a novel omni-directional image synthesis method, 2S-ODIS (Two-Stage Omni-Directional Image Synthesis), which generated high-quality omni-directional images but drastically reduced the training time. This was realized by utilizing the VQGAN (Vector Quantized GAN) model pre-trained on a large-scale NFoV image database such as ImageNet without fine-tuning. Since this pre-trained model does not represent distortions of omni-directional images in the equi-rectangular projection (ERP), it cannot be applied directly to the omni-directional image synthesis in ERP. Therefore, two-stage structure was adopted to first create a global coarse image in ERP and then refine the image by integrating multiple local NFoV images in the higher resolution to compensate the distortions in ERP, both of which are based on the pre-trained VQGAN model. As a result, the proposed method, 2S-ODIS, achieved the reduction of the training time from 14 days in OmniDreamer to four days in higher image quality.