Papers › DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection

21 Jul 2022arXiv:2207.10758archive 2025-07-28

Abhinav Kumar, Garrick Brazil, Enrique Corona, Armin Parchami, Xiaoming Liu

Modern neural networks use building blocks such as convolutions that are equivariant to arbitrary 2D translations. However, these vanilla blocks are not equivariant to arbitrary 3D translations in the projective manifold. Even then, all monocular 3D detectors use vanilla blocks to obtain the 3D coordinates, a task for which the vanilla blocks are not designed for. This paper takes the first step towards convolutions equivariant to arbitrary 3D translations in the projective manifold. Since the depth is the hardest to estimate for monocular detection, this paper proposes Depth EquiVarIAnt NeTwork (DEVIANT) built with existing scale equivariant steerable blocks. As a result, DEVIANT is equivariant to the depth translations in the projective manifold whereas vanilla networks are not. The additional depth equivariance forces the DEVIANT to learn consistent depth estimates, and therefore, DEVIANT achieves state-of-the-art monocular 3D detection results on KITTI and Waymo datasets in the image-only category and performs competitively to methods using extra information. Moreover, DEVIANT works better than vanilla networks in cross-dataset evaluation. Code and models at https://github.com/abhi1kumar/DEVIANT

PaperPDFCodeCode Syntology ran

In Syntology 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="2207.10758")

Code

Syntology Ran 9 of 15 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 2 ran · fixture could not drive it; 4 ran with no contract checked.

By repository: official repository: 4 samples from 1 repository, 3 ran; community (archive-listed): 11 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

abhi1kumar/deviant officialmentioned in papermentioned on GitHubpytorch report
abhi1kumar/seabird mentioned 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

15 samples harvested; 9 ran; 2 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
2ran · fixture could not drive it
4ran
6unverified

Licence: 0 of the 15 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 2 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.

hermite_poly abhi1kumar/deviant/lib/projective/ses_conv.py official repository ran · violated contract fingerprinted MIT (permissive) · 5681c96231f57592 · report
onescale_grid_hermite_gaussian abhi1kumar/deviant/lib/projective/ses_conv.py official repository ran · honoured contract fingerprinted MIT (permissive) · a55230bbf1f56fef · report
steerable_A abhi1kumar/deviant/lib/projective/ses_conv.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 12d0e5aad36f8a14 · report
SESConv_Z2_H abhi1kumar/deviant/lib/projective/ses_conv.py official repository unverified MIT (permissive) · 0430fe3332c4d37c · report
ErrorCorrectionModule abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) ran MIT (permissive) · 7c2136477d23f6ce · report
MergeFeaturesVF abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) ran fingerprinted MIT (permissive) · 61bbdc59f59741e6 · report
Perspective2OrthographicWarper abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) ran MIT (permissive) · 7cf468f83a7c217a · report
VerticalTransformer abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) ran MIT (permissive) · 6bbc2ddee8890789 · report
compute_M abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · bf014e5e0596b4fe · report
compute_intrinsic_matrix abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · da47b5a4e0059656 · report
FlatTransformer abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) unverified MIT (permissive) · 8575f6d6587b4b7d · report
TransformerVF abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) unverified MIT (permissive) · 535560f585c442c5 · report
compute_extrinsic_matrix abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) unverified MIT (permissive) · 6fd8cd04af32e79a · report
compute_homography abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) unverified MIT (permissive) · 807e9853a208792e · report
get_init_homography abhi1kumar/seabird/PanopticBEV/panoptic_bev/modules/transformer.py community (archive-listed) unverified MIT (permissive) · dd67f9b7c5c03b0a · report

Tasks

3D Object Detection3D Object Detection From Monocular ImagesMonocular 3D Object DetectionObject Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Object Detection From Monocular Images KITTI-360 DEVIANT AP25 26.96 #6 of 11 Archive leaderboard report
3D Object Detection From Monocular Images KITTI-360 DEVIANT AP50 0.88 #6 of 11 Archive leaderboard report
3D Object Detection From Monocular Images Waymo Open Dataset DEVIANT 3D mAPH Vehicle (Front Camera Only) 2.52 #1 of 3 Archive leaderboard report
Monocular 3D Object Detection KITTI Cars Moderate DEVIANT AP Medium 14.46 #8 of 29 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