3D Room Layouts From A Single RGB Panorama
10 papers with code • 3 benchmarks • 3 datasets
Image: Zou et al
Benchmarks
These leaderboards are used to track progress in 3D Room Layouts From A Single RGB Panorama
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
2D-3D-S
PanoContext
Rent3D
Most implemented papers
Corners for Layout: End-to-End Layout Recovery from 360 Images
The problem of 3D layout recovery in indoor scenes has been a core research topic for over a decade.
LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
zouchuhang/LayoutNetv2
•
•
CVPR 2018
We propose an algorithm to predict room layout from a single image that generalizes across panoramas and perspective images, cuboid layouts and more general layouts (e. g. L-shape room).
DuLa-Net: A Dual-Projection Network for Estimating Room Layouts from a Single RGB Panorama
SunDaDenny/DuLa-Net
•
•
CVPR 2019
We present a deep learning framework, called DuLa-Net, to predict Manhattan-world 3D room layouts from a single RGB panorama.
HorizonNet: Learning Room Layout with 1D Representation and Pano Stretch Data Augmentation
sunset1995/HorizonNet
•
•
CVPR 2019
We present a new approach to the problem of estimating the 3D room layout from a single panoramic image.
HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features
sunset1995/HoHoNet
•
•
CVPR 2021
We present HoHoNet, a versatile and efficient framework for holistic understanding of an indoor 360-degree panorama using a Latent Horizontal Feature (LHFeat).
SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama
Recent years have seen flourishing research on both semi-supervised learning and 3D room layout reconstruction.
LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering
Although significant progress has been made in room layout estimation, most methods aim to reduce the loss in the 2D pixel coordinate rather than exploiting the room structure in the 3D space.
OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas
A common approach has been to use standard convolutional networks to predict the corners and boundaries, followed by post-processing to generate the 3D layout.
3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform
starrah/dmh-net
•
•
We transform the image feature from a cubemap tile to the Hough space of a Manhattan world and directly map the feature to the geometric output.
