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 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="2203.07918")

Code

Syntology Ran 0 of 9 code samples harvested from 1 repository linked to this paper; 9 have no recorded run.

By repository: official repository: 9 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lolrudy/gpv_pose officialmentioned in papermentioned on GitHubpytorchMIT report
lolrudy/kp-red mentioned on GitHubpytorchApache-2.0 report
lolrudy/rbp_pose 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

9 samples harvested; 0 ran; 0 honoured the contract we drafted; 9 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.

9unverified

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. “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.

control_loss lolrudy/gpv_pose/engine/organize_loss.py official repository unverified MIT (permissive) · c26e5139544812be · report
defor_2D lolrudy/gpv_pose/datasets/data_augmentation.py official repository unverified MIT (permissive) · 1907108fce7bbe9a · report
defor_3D_bb lolrudy/gpv_pose/datasets/data_augmentation.py official repository unverified MIT (permissive) · 479152e874348de6 · report
defor_3D_bc lolrudy/gpv_pose/datasets/data_augmentation.py official repository unverified MIT (permissive) · d00ebddb21609c8d · report
expected_wrt_occupancy lolrudy/gpv_pose/nnutils/layers.py official repository unverified MIT (permissive) · b7549cd87fb0c3ec · report
expected_wrt_prob lolrudy/gpv_pose/nnutils/layers.py official repository unverified MIT (permissive) · 6709651c2a3bfacd · report
laplacian_cot lolrudy/gpv_pose/nnutils/laplacian_loss.py official repository unverified MIT (permissive) · 715f90a0136b95bb · report
mesh_laplacian_smoothing lolrudy/gpv_pose/nnutils/laplacian_loss.py official repository unverified MIT (permissive) · ac4d8b3cbad04fcc · report
occupancy_to_prob lolrudy/gpv_pose/nnutils/layers.py official repository 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