computer-vision-2

3D Room Layouts From A Single RGB Panorama

3260 papers • 126 benchmarks • 313 datasets

Image: Zou et al

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in 3d-room-layouts-from-a-single-rgb-panorama-2

Trend

Dataset

Best Model

Actions

Stanford2D3D Panoramic

PanoContext

Realtor360

Libraries

i

Use these libraries to find 3d-room-layouts-from-a-single-rgb-panorama-2 models and implementations

Datasets

2D-3D-S

PanoContext

Rent3D

Subtasks

No subtasks available.

Most implemented papers

Corners for Layout: End-to-End Layout Recovery From 360 Images

Javier Civera, Clara Fernandez-Labrador, José M. Fácil, Alejandro Pérez-Yus, C. Demonceaux, J. J. Guerrero•Mon Mar 18 2019

CFL (Corners for Layout), the first end-to-end model that predicts layout corners for 3D layout recovery on360 images, is presented, which outperform the state of the art, making less assumptions on the scene than other works, and with lower cost.

110

Content

Realtor360

0

Paper Graph

HorizonNet: Learning Room Layout With 1D Representation and Pano Stretch Data Augmentation

Hwann-Tzong Chen, Min Sun, Cheng Sun, Chi-Wei Hsiao•Fri Jan 11 2019

The proposed network, HorizonNet, trained for predicting 1D layout, outperforms previous state-of-the-art approaches and can diversify panorama data and be applied to other panorama-related learning tasks.

188 0

Paper Graph

DuLa-Net: A Dual-Projection Network for Estimating Room Layouts From a Single RGB Panorama

Peter Wonka, Chi-Han Peng, Hung-Kuo Chu, Min Sun, Shang-Ta Yang, Fu-En Wang•Wed Nov 28 2018

A deep learning framework, called DuLa-Net, to predict Manhattan-world 3D room layouts from a single RGB panorama that leverages two projections of the panorama at once, namely the equirectangular panorama-view and the perspective ceiling-view, that each contains different clues about the room layouts.

148 0

Paper Graph

LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image

Alex Colburn, Derek Hoiem, Chuhang Zou, Qi Shan•Thu Mar 22 2018

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) is proposed, which achieves among the best accuracy for perspective images and can handle both cuboid-shaped and moregeneral Manhattan layouts.

256 0

Paper Graph

HoHoNet: 360 Indoor Holistic Understanding with Latent Horizontal Features

Hwann-Tzong Chen, Min Sun, Cheng Sun•Sun Nov 22 2020

HoNet is a versatile and efficient framework for holistic understanding of an indoor 360-degree panorama using a Latent Horizontal Feature (LHFeat), and a novel horizon-to-dense module, which relaxes the per-column output shape constraint, allowing per-pixel dense prediction from LHFeat.

154 0

Paper Graph

SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama

Phi Vu Tran•Thu Dec 31 2020

This work proposes the first approach to learn representations of room corners and boundaries by using a combination of labeled and unlabeled data for improved layout estimation in a 360-degree panoramic scene.

3 0

Paper Graph

3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform

Yining Zhao, Chao Wen, Zhou Xue, Yue Gao•Mon Jul 18 2022

An alternative approach to estimate the walls in 3D space by modeling long-range geometric patterns in a learnable Hough Transform block by transforming the image feature from a cubemap tile to the Hough space of a Manhattan world and directly map the feature to the geometric output.

22 0

Paper Graph

Adding a benchmark result helps the community track progress.