PanoViT: Vision Transformer for Room Layout Estimation from a Single Panoramic Image
This work addresses the problem of estimating complex room layouts for applications in computer vision and robotics, representing an incremental advancement with novel adaptations for panoramic images.
The paper tackles room layout estimation from a single panoramic image by proposing PanoViT, a vision transformer that learns global information and includes modules for local feature extraction, resulting in improved accuracy over state-of-the-art methods on multiple datasets.
In this paper, we propose PanoViT, a panorama vision transformer to estimate the room layout from a single panoramic image. Compared to CNN models, our PanoViT is more proficient in learning global information from the panoramic image for the estimation of complex room layouts. Considering the difference between a perspective image and an equirectangular image, we design a novel recurrent position embedding and a patch sampling method for the processing of panoramic images. In addition to extracting global information, PanoViT also includes a frequency-domain edge enhancement module and a 3D loss to extract local geometric features in a panoramic image. Experimental results on several datasets demonstrate that our method outperforms state-of-the-art solutions in room layout prediction accuracy.