mlsanityData to 14 Oct 2026

PanoViT: Vision Transformer for Room Layout Estimation from a Single Panoramic Image

arXiv 2212.12156 ↗First posted 23 Dec 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 23 Dec 2022.

Builds on

17 of 23 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020Language Models are Few-Shot Learnerscited by 32,419
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2020End-to-End Object Detection with Transformerscited by 7,414
  7. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,253
  9. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,369
  10. 2020Strip Pooling: Rethinking Spatial Pooling for Scene Parsingcited by 114
  11. 2019HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentationcited by 108
  12. 2020HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Featurescited by 105
5 more
  1. 2018LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Imagecited by 95
  2. 2018DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panoramacited by 68
  3. 2021LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Renderingcited by 43
  4. 2016Pano2CAD: Room Layout From A Single Panorama Imagecited by 20
  5. 2019Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methodscited by 11

Built on by

Not cited yet.