Papers › Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images

5 May 2021CVPR 2021 1arXiv:2105.02047archive 2025-07-28

Florian Kluger, Hanno Ackermann, Eric Brachmann, Michael Ying Yang, Bodo Rosenhahn

Humans perceive and construct the surrounding world as an arrangement of simple parametric models. In particular, man-made environments commonly consist of volumetric primitives such as cuboids or cylinders. Inferring these primitives is an important step to attain high-level, abstract scene descriptions. Previous approaches directly estimate shape parameters from a 2D or 3D input, and are only able to reproduce simple objects, yet unable to accurately parse more complex 3D scenes. In contrast, we propose a robust estimator for primitive fitting, which can meaningfully abstract real-world environments using cuboids. A RANSAC estimator guided by a neural network fits these primitives to 3D features, such as a depth map. We condition the network on previously detected parts of the scene, thus parsing it one-by-one. To obtain 3D features from a single RGB image, we additionally optimise a feature extraction CNN in an end-to-end manner. However, naively minimising point-to-primitive distances leads to large or spurious cuboids occluding parts of the scene behind. We thus propose an occlusion-aware distance metric correctly handling opaque scenes. The proposed algorithm does not require labour-intensive labels, such as cuboid annotations, for training. Results on the challenging NYU Depth v2 dataset demonstrate that the proposed algorithm successfully abstracts cluttered real-world 3D scene layouts.

PaperPDFConference PDFCodeCode Syntology ran

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 13 code samples harvested from 1 repository linked to this paper: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 8 ran (8 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

fkluger/cuboids_revisited officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: 13 samples, 8 ran (0 instrument-failed) · 5 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

13 samples harvested: 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 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 · violated contract
7ran
5unverified

Licence: 0 of the 13 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 fkluger/cuboids_revisited. “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”. “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.

fkluger/cuboids_revisited official repository 13 samples, 8 ran (0 instrument-failed) · 5 unverified
fexp util/equal_distance_sampler_sq.py ran fingerprinted BSD-3-Clause (permissive) · f1547b350abc7741 · report fixture: signature x:ndarray/1/float, p:float/0/float · returned ndarray · level recorded 2026-09-25
manual_jacobian_x networks/layers.py ran BSD-3-Clause (permissive) · 2ae614a668daf19f · report fixture: signature y:Tensor/2/float, x:Tensor/3/float, create_graph:bool/0/bool · returned Tensor · level recorded 2026-09-25
rgb2gray in 27 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 2 of 3, arg 1: rank 3, kind float, dtype float32
datasets/smh.py ran · violated contract fingerprinted BSD-3-Clause (permissive) · eb7801586aa2560a · report fixture: signature rgb:ndarray/3/float · returned ndarray · level recorded 2026-09-22
sample_spherical datasets/synthetic_cuboids.py ran fingerprinted BSD-3-Clause (permissive) · 6a85549fd5684f82 · report fixture: signature ndim:int/0/int · returned ndarray · level recorded 2026-09-25
sigmoid in 216 papers
census: 36 implementations from 56 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
util/consistency.py ran fingerprinted BSD-3-Clause (permissive) · 78bb52ae71e528a9 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-25
sigmoid_ util/consistency.py ran fingerprinted BSD-3-Clause (permissive) · 13e6282360f1c5bb · report fixture: signature x:float/0/float · returned float · level recorded 2026-09-25
soft_inlier_fun_gen util/consistency.py ran BSD-3-Clause (permissive) · 00b04bc234d801ff · report fixture: signature beta:float/0/float, tau:float/0/float · returned function · level recorded 2026-09-25
sq_surface util/equal_distance_sampler_sq.py ran BSD-3-Clause (permissive) · ebb6838ea65260c2 · report fixture: signature a1:float/0/float, a2:float/0/float, a3:float/0/float, e1:float/0/float, e2:float/0/float, eta:float/0/float, omega:float/0/float · returned tuple · level recorded 2026-09-25
cuboid_mesh datasets/synthetic_cuboids.py unverified BSD-3-Clause (permissive) · 34820b208495b44c · report
e_step util/em_algorithm.py unverified BSD-3-Clause (permissive) · 40ed722d7c0a8379 · report
estimate_planes util/fitting.py unverified BSD-3-Clause (permissive) · c90770b4d4fe58ba · report
manual_jacobian_p networks/layers.py unverified BSD-3-Clause (permissive) · 7c81a4c434f45a23 · report
twist_to_matrix networks/pose_net.py unverified BSD-3-Clause (permissive) · 13a01a6a29372a67 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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