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 ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 41 code samples harvested from 3 repositories linked to this paper: 29 ran (of which 5 constructed an object rather than computing a result; 20 with no instrument failure: 2 honoured, 1 violated, 17 with no contract checked; 9 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 6 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 26 samples from 1 repository, 17 ran (9 with no instrument failure; 8 where Syntology's instrument failed); found in paper text by Syntology: 15 samples from 2 repositories, 12 ran (11 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

zhigangjiang/LGT-Net officialmentioned in papermentioned on GitHubpytorchSyntology: 26 samples, 17 ran (8 instrument-failed) · 9 unverified 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 (of which 5 constructed an object rather than computing a result; 20 with no instrument failure: 2 honoured, 1 violated, 17 with no contract checked; 9 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
3ran · our draft was wrong
6ran; the contract check could not run
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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

zhigangjiang/LGT-Net official repository 26 samples, 17 ran (8 instrument-failed) · 9 unverified
Densenet models/lgt_net.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 109c9c683735e627 · report fixture: signature x:Tensor/4/float · returned list · level recorded 2026-09-22
GlobalHeightConv models/lgt_net.py ran · metamorphic tier: invariant MIT (permissive) · f426aea9794d835b · report fixture: signature x:Tensor/4/float, out_w:int/0/int · returned Tensor · level recorded 2026-09-22
GlobalHeightStage models/lgt_net.py ran · metamorphic tier: well formed MIT (permissive) · 046d307a8924dd40 · report fixture: signature conv_list:list/1/Tensor, out_w:int/0/int · returned Tensor · level recorded 2026-09-22
LR_PAD models/lgt_net.py ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e7020a950934c896 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
PatchFeatureExtractor models/lgt_net.py ran · metamorphic tier: invariant MIT (permissive) · 2c25056c0bbdf3d4 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-22
Resnet in 6 papers models/lgt_net.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a17be21fd7667d1d · report fixture: signature x:Tensor/4/float · returned list · level recorded 2026-09-22
lonlat2depth models/lgt_net.py ran; the contract check could not run (DEP_MISSING) fingerprinted MIT (permissive) · 6cef8604f8e31f90 · report fixture: signature lonlat:Tensor/2/float, plan_y:float/0/float · returned Tensor · level recorded 2026-09-22
lonlat2uv models/lgt_net.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · e08b230379520210 · report fixture: signature lonlat:ndarray/3/float, axis:NoneType/0/? · returned ndarray · level recorded 2026-09-22
lonlat2xyz models/lgt_net.py ran · honoured contract fingerprinted MIT (permissive) · 4bc801ccb54cea0d · report fixture: signature lonlat:ndarray/3/float, plan_y:float/0/float · returned ndarray · level recorded 2026-09-22
lr_pad models/lgt_net.py ran · our draft was wrong fingerprinted MIT (permissive) · 05bb0fc14c5b2e6f · report fixture: signature x:Tensor/4/float, padding:int/0/int · returned Tensor · level recorded 2026-09-22
lsq_fit models/lgt_net.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 3b6d4e30949d4351 · report fixture: signature ceil_norm:ndarray/1/float, floor_norm:ndarray/1/float · returned float64 · level recorded 2026-09-22
mean_percentile_fit models/lgt_net.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d496b87bfe4f28df · report fixture: signature ceil_norm:ndarray/1/float, floor_norm:ndarray/1/float, p1:int/0/int, p2:int/0/int · returned float64 · level recorded 2026-09-22
pixel2lonlat models/lgt_net.py ran · our draft was wrong fingerprinted MIT (permissive) · 0f830e436112af8c · report fixture: signature pixel:Tensor/2/float, w:int/0/int, h:int/0/int, axis:NoneType/0/? · returned Tensor · level recorded 2026-09-22
tensor2np in 5 papers models/lgt_net.py ran · honoured contract MIT (permissive) · 922a504a7290fc87 · report fixture: signature t:Tensor/2/float · returned ndarray · level recorded 2026-09-22
uv2depth models/lgt_net.py ran; the contract check could not run (DEP_MISSING) MIT (permissive) · 23b5aa6a5eacf714 · report fixture: signature uv:Tensor/3/float, plan_y:NoneType/0/? · returned Tensor · level recorded 2026-09-22
uv2lonlat models/lgt_net.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · 47924572be94e478 · report fixture: signature uv:ndarray/3/float, axis:NoneType/0/? · returned ndarray · level recorded 2026-09-22
xyz2depth models/lgt_net.py ran · violated contract fingerprinted MIT (permissive) · 02da98b9fd3b4110 · report fixture: signature xyz:Tensor/2/float, plan_y:float/0/float · returned Tensor · level recorded 2026-09-22
BaseModule in 10 papers models/lgt_net.py unverified MIT (permissive) · 9964cf34a550253f · report
HorizonNetFeatureExtractor models/lgt_net.py unverified MIT (permissive) · 4a1a17be2090564a · report
LGT_Net models/lgt_net.py unverified MIT (permissive) · 835f2d98ab88d099 · report
calc_ceil_ratio models/lgt_net.py unverified MIT (permissive) · 85e4cb8a34e05ae6 · report
get_lon models/lgt_net.py unverified MIT (permissive) · d4a6a478df38b6ab · report
get_u models/lgt_net.py unverified MIT (permissive) · 55708de368ac7f66 · report
pixel2uv models/lgt_net.py unverified MIT (permissive) · dea4ff3b24e71bf9 · report
uv2xyz models/lgt_net.py unverified MIT (permissive) · 2be742bce4a40c80 · report
wrap_lr_pad models/lgt_net.py unverified MIT (permissive) · 85f1cf23e76e1df3 · report
sunset1995/HorizonNet found in paper text by Syntology 9 samples, 6 ran (1 instrument-failed) · 3 unverified
ConvCompressH model.py ran fingerprinted MIT (permissive) · 598460a88f0ac62e · report fixture: returned ConvCompressH · level recorded 2026-09-22
Densenet model.py ran MIT (permissive) · cdea203aeb719375 · report fixture: returned Densenet · level recorded 2026-09-22
GlobalHeightConv model.py ran MIT (permissive) · e026379ae7df54b2 · report fixture: returned GlobalHeightConv · level recorded 2026-09-22
GlobalHeightStage model.py ran MIT (permissive) · e0b742101d2c3d03 · report fixture: returned GlobalHeightStage · level recorded 2026-09-22
LR_PAD model.py ran fingerprinted MIT (permissive) · b4de71f09433e917 · report fixture: returned LR_PAD · level recorded 2026-09-22
lr_pad model.py ran · our draft was wrong fingerprinted MIT (permissive) · fb884f33b5fda8ea · report fixture: signature x:Tensor/4/float, padding:int/0/int · returned Tensor · level recorded 2026-09-22
HorizonNet model.py unverified MIT (permissive) · 7bc64cd9d682d874 · report
Resnet in 6 papers model.py unverified MIT (permissive) · c72c9c34cc506636 · report
wrap_lr_pad model.py unverified MIT (permissive) · 8c7e4f0e8cfcb68c · report
zillow/zind found in paper text by Syntology 6 samples, 6 ran (0 instrument-failed) · 0 unverified
angle_between_vectors code/partition_zind.py ran fingerprinted Apache-2.0 (permissive) · a004fe2c7e365c9c · report fixture: signature vector1:ndarray/1/float, vector2:ndarray/1/float · returned float64 · level recorded 2026-09-24
calculate_checksum download_data.py ran Apache-2.0 (permissive) · 097a499dece27df2 · report fixture: signature dest_path:str/0/str · returned str · level recorded 2026-09-24
get_angle_distribution code/partition_zind.py ran fingerprinted Apache-2.0 (permissive) · 95b35410f31c1f3f · report fixture: signature room_vertices:ndarray/2/float · returned list · level recorded 2026-09-24
get_layout_type code/partition_zind.py ran Apache-2.0 (permissive) · ebfe1d039da0f3e3 · report fixture: signature room_vertices:ndarray/2/float, threshold_degrees:int/0/int · returned str · level recorded 2026-09-24
keep_required_keys download_data.py ran Apache-2.0 (permissive) · 74801c7a2efa6e63 · report fixture: signature local_house_dict:dict/0/? · returned dict · level recorded 2026-09-24
run_imap_unordered_multiprocessing download_data.py ran Apache-2.0 (permissive) · 4cedaf232c882f16 · report fixture: signature func:callable/0/?, argument_list:list/1/int, num_processes:int/0/int · returned list · level recorded 2026-09-24

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for LGT-Net (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for LGT-Net (graph method: LGT-Net). 9 bricks; individually on a fixture: 6 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. HorizonNet entry · level 0 · unverified · 7bc64cd9d682d874
  2. Densenet model · level 1 · ran · cdea203aeb719375
  3. GlobalHeightStage helper · level 1 · ran · e0b742101d2c3d03
  4. Resnet model · level 0 · unverified · c72c9c34cc506636
  5. wrap_lr_pad helper · level 0 · unverified · 8c7e4f0e8cfcb68c
  6. GlobalHeightConv helper · level 1 · ran · e026379ae7df54b2
  7. LR_PAD helper · level 1 · ran · b4de71f09433e917
  8. ConvCompressH helper · level 1 · ran · 598460a88f0ac62e
  9. lr_pad helper · level 1 · ran · our draft was wrong · fb884f33b5fda8ea

harvested Assembly for LGT-Net (graph method: LGT-Net). 27 bricks; individually on a fixture: 18 ran (of which 1 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 1 violated, 7 with no contract checked; 8 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. LGT_Net entry · level 0 · unverified · 835f2d98ab88d099
  2. BaseModule helper · level 0 · unverified · 9964cf34a550253f
  3. HorizonNetFeatureExtractor helper · level 0 · unverified · 4a1a17be2090564a
  4. PatchFeatureExtractor helper · level 1 · ran · 2c25056c0bbdf3d4
  5. calc_ceil_ratio helper · level 0 · unverified · 85e4cb8a34e05ae6
  6. get_lon helper · level 0 · unverified · d4a6a478df38b6ab
  7. get_u helper · level 0 · unverified · 55708de368ac7f66
  8. lonlat2depth helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 6cef8604f8e31f90
  9. lonlat2uv helper · level 1 · ran; the contract check could not run (RAISES) · e08b230379520210
  10. tensor2np helper · level 1 · ran · honoured contract · 922a504a7290fc87
  11. uv2depth helper · level 1 · ran; the contract check could not run (DEP_MISSING) · 23b5aa6a5eacf714
  12. Densenet helper · level 1 · ran · 109c9c683735e627
  13. GlobalHeightStage helper · level 1 · ran · 046d307a8924dd40
  14. Resnet helper · level 1 · ran · a17be21fd7667d1d
  15. wrap_lr_pad helper · level 0 · unverified · 85f1cf23e76e1df3
  16. lsq_fit helper · level 1 · ran; the contract check could not run (RAISES) · 3b6d4e30949d4351
  17. mean_percentile_fit helper · level 1 · ran; the contract check could not run (RAISES) · d496b87bfe4f28df
  18. uv2xyz helper · level 0 · unverified · 2be742bce4a40c80
  19. pixel2lonlat helper · level 1 · ran · our draft was wrong · 0f830e436112af8c
  20. pixel2uv helper · level 0 · unverified · dea4ff3b24e71bf9
  21. lonlat2xyz helper · level 1 · ran · honoured contract · 4bc801ccb54cea0d
  22. xyz2depth helper · level 1 · ran · violated contract · 02da98b9fd3b4110
  23. GlobalHeightConv helper · level 1 · ran · f426aea9794d835b
  24. LR_PAD helper · level 1 · ran · e7020a950934c896
  25. uv2lonlat helper · level 1 · ran; the contract check could not run (RAISES) · 47924572be94e478
  26. ConvCompressH helper · level 1 · ran · 598460a88f0ac62e
  27. lr_pad helper · level 1 · ran · our draft was wrong · 05bb0fc14c5b2e6f

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2203.01824") returns these assemblies with each brick's role and wiring (how to connect).

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