Papers › GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting

15 Mar 2022CVPR 2022 1arXiv:2203.07918archive 2025-07-28

Yan Di, Ruida Zhang, Zhiqiang Lou, Fabian Manhardt, Xiangyang Ji, Nassir Navab, Federico Tombari

While 6D object pose estimation has recently made a huge leap forward, most methods can still only handle a single or a handful of different objects, which limits their applications. To circumvent this problem, category-level object pose estimation has recently been revamped, which aims at predicting the 6D pose as well as the 3D metric size for previously unseen instances from a given set of object classes. This is, however, a much more challenging task due to severe intra-class shape variations. To address this issue, we propose GPV-Pose, a novel framework for robust category-level pose estimation, harnessing geometric insights to enhance the learning of category-level pose-sensitive features. First, we introduce a decoupled confidence-driven rotation representation, which allows geometry-aware recovery of the associated rotation matrix. Second, we propose a novel geometry-guided point-wise voting paradigm for robust retrieval of the 3D object bounding box. Finally, leveraging these different output streams, we can enforce several geometric consistency terms, further increasing performance, especially for non-symmetric categories. GPV-Pose produces superior results to state-of-the-art competitors on common public benchmarks, whilst almost achieving real-time inference speed at 20 FPS.

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 9 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 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: 9 samples from 1 repository, 6 ran (6 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.

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

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

lolrudy/gpv_pose officialmentioned in papermentioned on GitHubpytorchMITSyntology: 9 samples, 6 ran (0 instrument-failed) · 3 unverified report
lolrudy/kp-red mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation (arXiv:2403.10099; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
lolrudy/rbp_pose mentioned on GitHubpytorchSyntology: not harvested 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

9 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 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.

6ran
3unverified

Licence: 0 of the 9 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 lolrudy/gpv_pose. “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.

lolrudy/gpv_pose official repository 9 samples, 6 ran (0 instrument-failed) · 3 unverified
control_loss engine/organize_loss.py ran MIT (permissive) · c26e5139544812be · report fixture: signature Train_stage:str/0/str · returned tuple · level recorded 2026-09-24
defor_2D datasets/data_augmentation.py ran MIT (permissive) · 1907108fce7bbe9a · report fixture: signature roi_mask:ndarray/2/float, rand_r:int/0/int, rand_pro:float/0/float · returned ndarray · level recorded 2026-09-24
defor_3D_bb datasets/data_augmentation.py ran MIT (permissive) · 479152e874348de6 · report fixture: signature pc:Tensor/2/float, R:Tensor/2/float, t:Tensor/1/float, s:Tensor/1/float, sym:list/1/int, aug_bb:list/1/float · returned tuple · level recorded 2026-09-24
defor_3D_bc datasets/data_augmentation.py ran MIT (permissive) · d00ebddb21609c8d · report fixture: signature pc:Tensor/2/float, R:Tensor/2/float, t:Tensor/1/float, s:Tensor/1/float, model_point:Tensor/2/float, nocs_scale:float/0/float · returned tuple · level recorded 2026-09-24
expected_wrt_prob nnutils/layers.py ran MIT (permissive) · 6709651c2a3bfacd · report fixture: signature value:Tensor/5/float, prob:Tensor/5/float, miss:float/0/float · returned Tensor · level recorded 2026-09-24
laplacian_cot nnutils/laplacian_loss.py ran MIT (permissive) · 715f90a0136b95bb · report fixture: signature meshes:MockMeshes/0/? · returned tuple · level recorded 2026-09-24
expected_wrt_occupancy nnutils/layers.py unverified MIT (permissive) · b7549cd87fb0c3ec · report
mesh_laplacian_smoothing nnutils/laplacian_loss.py unverified MIT (permissive) · ac4d8b3cbad04fcc · report
occupancy_to_prob nnutils/layers.py unverified MIT (permissive) · ded17a074ea35ec9 · report

Tasks

6D Pose Estimation6D Pose Estimation using RGB6D Pose Estimation using RGBDObjectPose EstimationRetrieval

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
6D Pose Estimation LineMOD GPV-Pose Mean ADD-S 98.2 #5 of 5 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose FPS 20 #3 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose mAP 10, 10cm 74.6 #3 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose mAP 10, 5cm 73.3 #3 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose mAP 3DIou@25 84.2 #3 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose mAP 3DIou@50 83 #3 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose mAP 3DIou@75 64.4 #3 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose mAP 5, 2cm 32 #3 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 GPV-Pose mAP 5, 5cm 42.9 #3 of 11 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.

Methods

SPEED

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