Papers › iDisc: Internal Discretization for Monocular Depth Estimation

iDisc: Internal Discretization for Monocular Depth Estimation

13 Apr 2023CVPR 2023 1arXiv:2304.06334archive 2025-07-28

Luigi Piccinelli, Christos Sakaridis, Fisher Yu

Monocular depth estimation is fundamental for 3D scene understanding and downstream applications. However, even under the supervised setup, it is still challenging and ill-posed due to the lack of full geometric constraints. Although a scene can consist of millions of pixels, there are fewer high-level patterns. We propose iDisc to learn those patterns with internal discretized representations. The method implicitly partitions the scene into a set of high-level patterns. In particular, our new module, Internal Discretization (ID), implements a continuous-discrete-continuous bottleneck to learn those concepts without supervision. In contrast to state-of-the-art methods, the proposed model does not enforce any explicit constraints or priors on the depth output. The whole network with the ID module can be trained end-to-end, thanks to the bottleneck module based on attention. Our method sets the new state of the art with significant improvements on NYU-Depth v2 and KITTI, outperforming all published methods on the official KITTI benchmark. iDisc can also achieve state-of-the-art results on surface normal estimation. Further, we explore the model generalization capability via zero-shot testing. We observe the compelling need to promote diversification in the outdoor scenario. Hence, we introduce splits of two autonomous driving datasets, DDAD and Argoverse. Code is available at http://vis.xyz/pub/idisc .

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 6 code samples harvested from 1 repository linked to this paper: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 5 ran (3 with no instrument failure; 2 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

SysCV/idisc officialmentioned on GitHubpytorchSyntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
lpiccinelli-eth/unidepth mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to UniDepth: Universal Monocular Metric Depth Estimation (arXiv:2403.18913; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 11 where Syntology's instrument failed) · 10 unverified) and UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler (arXiv:2502.20110; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

6 samples harvested: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 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 · our draft was wrong
3ran
1unverified

Licence: 6 of the 6 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 SysCV/idisc. “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 1 sample 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

SysCV/idisc official repository 6 samples, 5 ran (2 instrument-failed) · 1 unverified
AttentionLayer in 30 papers idisc/models/id_module.py ran licence not identified · pointer only · c2e0047d60b9f291 · report fixture: returned AttentionLayer · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
idisc/models/id_module.py ran fingerprinted licence not identified · pointer only · 9fd176b1d81fef0d · report fixture: returned LayerNorm · level recorded 2026-09-22
PositionEmbeddingSine in 21 papers
census: 6 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 4, kind float, dtype float32
idisc/models/id_module.py ran · metamorphic tier: invariant fingerprinted licence not identified · pointer only · 31f137df1d61458e · report fixture: signature x:Tensor/4/float, mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
_get_activation_cls idisc/models/id_module.py ran · our draft was wrong licence not identified · pointer only · e220cdd4017ddf4d · report fixture: signature activation:str/0/str · returned ReLU · level recorded 2026-09-22
get_norm in 48 papers idisc/models/id_module.py ran · our draft was wrong licence not identified · pointer only · ab2364408642790f · report fixture: signature norm:str/0/str, out_channels:int/0/int · returned BatchNorm2d · level recorded 2026-09-22
ISDHead idisc/models/id_module.py unverified licence not identified · pointer only · 6aba889a320ff6eb · 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 Internal Discretization (ID) (graph method: Internal Discretization (ID)). 6 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. ISDHead entry · level 0 · unverified · 6aba889a320ff6eb
  2. AttentionLayer helper · level 1 · ran · c2e0047d60b9f291
  3. PositionEmbeddingSine helper · level 1 · ran · 31f137df1d61458e
  4. _get_activation_cls helper · level 1 · ran · our draft was wrong · e220cdd4017ddf4d
  5. get_norm helper · level 1 · ran · our draft was wrong · ab2364408642790f
  6. LayerNorm helper · level 1 · ran · 9fd176b1d81fef0d

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="2304.06334") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Autonomous DrivingDepth EstimationMonocular Depth EstimationScene UnderstandingSurface Normal EstimationSurface Normals Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split iDisc Delta < 1.25 0.977 #21 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split iDisc Delta < 1.25^2 0.997 #21 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split iDisc Delta < 1.25^3 0.999 #21 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split iDisc RMSE 2.067 #21 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split iDisc RMSE log 0.077 #21 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split iDisc Sq Rel 0.145 #21 of 79 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split iDisc absolute relative error 0.050 #21 of 79 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 iDisc Delta < 1.25^2 0.993 #32 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 iDisc Delta < 1.25^3 0.999 #32 of 85 Archive leaderboard report
Monocular Depth Estimation NYU-Depth V2 iDisc absolute relative error 0.086 #32 of 85 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 iDisc % < 11.25 63.8 #3 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 iDisc % < 22.5 79.8 #3 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 iDisc % < 30 85.6 #3 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 iDisc Mean Angle Error 14.6 #3 of 6 Archive leaderboard report
Surface Normals Estimation NYU Depth v2 iDisc RMSE 22.8 #3 of 6 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