Papers › LocalBins: Improving Depth Estimation by Learning Local Distributions

LocalBins: Improving Depth Estimation by Learning Local Distributions

28 Mar 2022arXiv:2203.15132archive 2025-07-28

Shariq Farooq Bhat, Ibraheem Alhashim, Peter Wonka

We propose a novel architecture for depth estimation from a single image. The architecture itself is based on the popular encoder-decoder architecture that is frequently used as a starting point for all dense regression tasks. We build on AdaBins which estimates a global distribution of depth values for the input image and evolve the architecture in two ways. First, instead of predicting global depth distributions, we predict depth distributions of local neighborhoods at every pixel. Second, instead of predicting depth distributions only towards the end of the decoder, we involve all layers of the decoder. We call this new architecture LocalBins. Our results demonstrate a clear improvement over the state-of-the-art in all metrics on the NYU-Depth V2 dataset. Code and pretrained models will be made publicly available.

PaperPDFCodeCode 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 14 code samples harvested from 1 repository linked to this paper: 11 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 14 samples from 1 repository, 11 ran (11 with no instrument failure; 0 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.

shariqfarooq123/localbins officialmentioned in paperpytorchSyntology: 14 samples, 11 ran (0 instrument-failed) · 3 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

14 samples harvested: 11 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 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.

1ran · honoured contract
10ran
3unverified

Licence: 14 of the 14 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 shariqfarooq123/localbins. “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 5 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.

shariqfarooq123/localbins official repository 14 samples, 11 ran (0 instrument-failed) · 3 unverified
DecoderBN models/localbins.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 94c5b7d2b4302b58 · report fixture: returned DecoderBN · level recorded 2026-09-22
DenseNet161 models/localbins.py ran fingerprinted GPL-3.0 (copyleft) · pointer only · 3da118be1e97c0ab · report fixture: signature x:Tensor/4/float · returned list · level recorded 2026-09-24
Encoder in 278 papers models/localbins.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 61ba7e7902884a5d · report fixture: returned Encoder · level recorded 2026-09-22
IdentitySplitter models/localbins.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 40cfa5c2ac71618f · report fixture: returned IdentitySplitter · level recorded 2026-09-22
LinearSplitter models/localbins.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 3ea1b754faaf2f5f · report fixture: returned LinearSplitter · level recorded 2026-09-22
NaiveSplitter models/localbins.py ran GPL-3.0 (copyleft) · pointer only · 2644b40b12c023ae · report fixture: signature x:Tensor/4/float, b_prev:Tensor/4/float, prev_b_embedding:Tensor/4/float, interpolate:bool/0/bool, is_for_query:bool/0/bool · returned tuple · level recorded 2026-09-24
Projector in 18 papers models/localbins.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · 7f9272262523dd47 · report fixture: returned Projector · level recorded 2026-09-22
SeedBinRegressor models/localbins.py ran · metamorphic tier: deterministic GPL-3.0 (copyleft) · pointer only · eccbd8f04ac02f35 · report fixture: returned SeedBinRegressor · level recorded 2026-09-22
SigmoidSplitter models/localbins.py ran GPL-3.0 (copyleft) · pointer only · 0362753091014ef8 · report fixture: signature x:Tensor/4/float, b_prev:Tensor/4/float, prev_b_embedding:Tensor/4/float, interpolate:bool/0/bool, is_for_query:bool/0/bool · returned tuple · level recorded 2026-09-24
UpSampleBN models/localbins.py ran · metamorphic tier: deterministic fingerprinted GPL-3.0 (copyleft) · pointer only · 60a23709ff31b1ce · report fixture: returned UpSampleBN · level recorded 2026-09-22
positionalencoding2d in 17 papers models/localbins.py ran · honoured contract GPL-3.0 (copyleft) · pointer only · 486a705761f533bf · report fixture: signature d_model:int/0/int, height:int/0/int, width:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-22
EfficientNet in 7 papers models/localbins.py unverified GPL-3.0 (copyleft) · pointer only · 174989f235ede289 · report
UnetLocalBins models/localbins.py unverified GPL-3.0 (copyleft) · pointer only · 699d414fe9fb2cc2 · report
build_encoder in 17 papers models/localbins.py unverified GPL-3.0 (copyleft) · pointer only · 220bad915281cbcc · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for LocalBins (graph method: LocalBins). 14 bricks; individually on a fixture: 11 ran (of which 7 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. UnetLocalBins entry · level 0 · unverified · 699d414fe9fb2cc2
  2. DecoderBN model · level 1 · ran · 94c5b7d2b4302b58
  3. build_encoder helper · level 0 · unverified · 220bad915281cbcc
  4. IdentitySplitter model · level 1 · ran · 40cfa5c2ac71618f
  5. LinearSplitter model · level 1 · ran · 3ea1b754faaf2f5f
  6. NaiveSplitter model · level 1 · ran · 2644b40b12c023ae
  7. Projector model · level 1 · ran · 7f9272262523dd47
  8. SeedBinRegressor model · level 1 · ran · eccbd8f04ac02f35
  9. SigmoidSplitter model · level 1 · ran · 0362753091014ef8
  10. UpSampleBN helper · level 1 · ran · 60a23709ff31b1ce
  11. DenseNet161 helper · level 1 · ran · 3da118be1e97c0ab
  12. EfficientNet helper · level 0 · unverified · 174989f235ede289
  13. positionalencoding2d helper · level 1 · ran · honoured contract · 486a705761f533bf
  14. Encoder model · level 1 · ran · 61ba7e7902884a5d

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="2203.15132") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

AllDecoderDepth EstimationMonocular Depth Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation NYU-Depth V2 LocalBins Delta < 1.25 0.91 #47 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LocalBins Delta < 1.25^2 0.986 #47 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LocalBins Delta < 1.25^3 0.997 #47 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LocalBins RMSE 0.351 #47 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LocalBins absolute relative error 0.098 #47 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 LocalBins log 10 0.042 #47 of 85 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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