Open-source alternatives to HorizonNet

This is the implementation of our paper

This repository contains the official implementation of the paper "Unposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model". Accepted by ICLR 2025. [arXiv](https://arxiv.org/abs/2502.16779)

This is the implementation of our CVPRW'21 paper " OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas " accepted at the 2nd workshop on Omnidirectional Computer Vision.

DMH-Net Code for 3D Room Layout Estimation from a Cubemap of Panorama Image via Deep Manhattan Hough Transform (ECCV 2022)

This repository contains the code and models for the paper "Single-Shot Cuboids: Geodesics-based End-to-end Manhattan Aligned Layout Estimation from Spherical Panoramas".

Code of my CVPR'16 paper: "Efficient 3D Room Shape Recovery From a Single Panorama."

Pytorch implementation of "Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness" (CVPR'23) The project is reproduced based on LGT-Net and PanoFormer. The generating mask process can be found in generatesegmentation-mask.py. Download…

Created by Haiyan Wang, Will Hutchcroft, Yuguang Li, Zhiqiang Wan, Ivaylo Boyadzhiev, Yingli Tian, Sing Bing Kang from Zillow and The City College of New York .

Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image"

Tensorflow implementation of our end-to-end model to recover 3D layouts of indoor scenes.

PyTorch implementation of our IJCV paper: