Papers › LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

LGT-Net: Indoor Panoramic Room Layout Estimation with Geometry-Aware Transformer Network

3 Mar 2022CVPR 2022 1arXiv:2203.01824archive 2025-07-28

Zhigang Jiang, Zhongzheng Xiang, Jinhua Xu, Ming Zhao

3D room layout estimation by a single panorama using deep neural networks has made great progress. However, previous approaches can not obtain efficient geometry awareness of room layout with the only latitude of boundaries or horizon-depth. We present that using horizon-depth along with room height can obtain omnidirectional-geometry awareness of room layout in both horizontal and vertical directions. In addition, we propose a planar-geometry aware loss function with normals and gradients of normals to supervise the planeness of walls and turning of corners. We propose an efficient network, LGT-Net, for room layout estimation, which contains a novel Transformer architecture called SWG-Transformer to model geometry relations. SWG-Transformer consists of (Shifted) Window Blocks and Global Blocks to combine the local and global geometry relations. Moreover, we design a novel relative position embedding of Transformer to enhance the spatial identification ability for the panorama. Experiments show that the proposed LGT-Net achieves better performance than current state-of-the-arts (SOTA) on benchmark datasets.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2203.01824")

Code

Syntology Ran 29 of 41 code samples harvested from 3 repositories linked to this paper; 12 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 3 ran · our draft was wrong; 6 ran · fixture could not drive it; 17 ran with no contract checked.

By repository: official repository: 26 samples from 1 repository, 17 ran; found in paper text by Syntology: 15 samples from 2 repositories, 12 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zhigangjiang/LGT-Net officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

41 samples harvested; 29 ran; 2 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
6ran · fixture could not drive it
17ran
12unverified

Licence: 0 of the 41 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

Densenet zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 109c9c683735e627 · report
GlobalHeightConv zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · metamorphic tier: invariant MIT (permissive) · f426aea9794d835b · report
GlobalHeightStage zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · metamorphic tier: well formed MIT (permissive) · 046d307a8924dd40 · report
LR_PAD zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e7020a950934c896 · report
PatchFeatureExtractor zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · metamorphic tier: invariant MIT (permissive) · 2c25056c0bbdf3d4 · report
Resnet zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a17be21fd7667d1d · report
lonlat2depth zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 6cef8604f8e31f90 · report
lonlat2uv zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · e08b230379520210 · report
lonlat2xyz zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · honoured contract fingerprinted MIT (permissive) · 4bc801ccb54cea0d · report
lr_pad zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 05bb0fc14c5b2e6f · report
lsq_fit zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3b6d4e30949d4351 · report
mean_percentile_fit zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · d496b87bfe4f28df · report
pixel2lonlat zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 0f830e436112af8c · report
tensor2np zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · honoured contract MIT (permissive) · 922a504a7290fc87 · report
uv2depth zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · fixture could not drive it MIT (permissive) · 23b5aa6a5eacf714 · report
uv2lonlat zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 47924572be94e478 · report
xyz2depth zhigangjiang/LGT-Net/models/lgt_net.py official repository ran · violated contract fingerprinted MIT (permissive) · 02da98b9fd3b4110 · report
BaseModule zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · 9964cf34a550253f · report
HorizonNetFeatureExtractor zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · 4a1a17be2090564a · report
LGT_Net zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · 835f2d98ab88d099 · report
calc_ceil_ratio zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · 85e4cb8a34e05ae6 · report
get_lon zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · d4a6a478df38b6ab · report
get_u zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · 55708de368ac7f66 · report
pixel2uv zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · dea4ff3b24e71bf9 · report
uv2xyz zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · 2be742bce4a40c80 · report
wrap_lr_pad zhigangjiang/LGT-Net/models/lgt_net.py official repository unverified MIT (permissive) · 85f1cf23e76e1df3 · report
ConvCompressH sunset1995/HorizonNet/model.py found in paper text by Syntology ran fingerprinted MIT (permissive) · 598460a88f0ac62e · report
Densenet sunset1995/HorizonNet/model.py found in paper text by Syntology ran MIT (permissive) · cdea203aeb719375 · report
GlobalHeightConv sunset1995/HorizonNet/model.py found in paper text by Syntology ran MIT (permissive) · e026379ae7df54b2 · report
GlobalHeightStage sunset1995/HorizonNet/model.py found in paper text by Syntology ran MIT (permissive) · e0b742101d2c3d03 · report
LR_PAD sunset1995/HorizonNet/model.py found in paper text by Syntology ran fingerprinted MIT (permissive) · b4de71f09433e917 · report
angle_between_vectors zillow/zind/code/partition_zind.py found in paper text by Syntology ran fingerprinted Apache-2.0 (permissive) · a004fe2c7e365c9c · report
calculate_checksum zillow/zind/download_data.py found in paper text by Syntology ran Apache-2.0 (permissive) · 097a499dece27df2 · report
get_angle_distribution zillow/zind/code/partition_zind.py found in paper text by Syntology ran Apache-2.0 (permissive) · 95b35410f31c1f3f · report
get_layout_type zillow/zind/code/partition_zind.py found in paper text by Syntology ran Apache-2.0 (permissive) · ebfe1d039da0f3e3 · report
keep_required_keys zillow/zind/download_data.py found in paper text by Syntology ran Apache-2.0 (permissive) · 74801c7a2efa6e63 · report
lr_pad sunset1995/HorizonNet/model.py found in paper text by Syntology ran · our draft was wrong fingerprinted MIT (permissive) · fb884f33b5fda8ea · report
run_imap_unordered_multiprocessing zillow/zind/download_data.py found in paper text by Syntology ran Apache-2.0 (permissive) · 4cedaf232c882f16 · report
HorizonNet sunset1995/HorizonNet/model.py found in paper text by Syntology unverified MIT (permissive) · 7bc64cd9d682d874 · report
Resnet sunset1995/HorizonNet/model.py found in paper text by Syntology unverified MIT (permissive) · c72c9c34cc506636 · report
wrap_lr_pad sunset1995/HorizonNet/model.py found in paper text by Syntology unverified MIT (permissive) · 8c7e4f0e8cfcb68c · report

Tasks

Room Layout Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAWAREAbsolute Position EncodingsAdamAttentionAverage PoolingBPEBatch NormalizationBottleneck Residual BlockConvolutionDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationLabel SmoothingLayer NormalizationLinear LayerMax PoolingMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual BlockResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections