Papers › Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation

9 Jan 2019CVPR 2019 6arXiv:1901.02970archive 2025-07-28

He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas

The goal of this paper is to estimate the 6D pose and dimensions of unseen object instances in an RGB-D image. Contrary to "instance-level" 6D pose estimation tasks, our problem assumes that no exact object CAD models are available during either training or testing time. To handle different and unseen object instances in a given category, we introduce a Normalized Object Coordinate Space (NOCS)---a shared canonical representation for all possible object instances within a category. Our region-based neural network is then trained to directly infer the correspondence from observed pixels to this shared object representation (NOCS) along with other object information such as class label and instance mask. These predictions can be combined with the depth map to jointly estimate the metric 6D pose and dimensions of multiple objects in a cluttered scene. To train our network, we present a new context-aware technique to generate large amounts of fully annotated mixed reality data. To further improve our model and evaluate its performance on real data, we also provide a fully annotated real-world dataset with large environment and instance variation. Extensive experiments demonstrate that the proposed method is able to robustly estimate the pose and size of unseen object instances in real environments while also achieving state-of-the-art performance on standard 6D pose estimation benchmarks.

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

The archive's official repository (hughw19/NOCS_CVPR2019) was not harvested; the 20 samples below come from 2 community repositories.

Syntology 20 code samples harvested from 2 repositories linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 2 repositories, 18 ran (16 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 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

hughw19/NOCS_CVPR2019 officialmentioned on GitHubtfNOASSERTIONSyntology: not harvested report
YuhangMing/Object-Guided-Relocalisation mentioned on GitHubtfSyntology: not harvested report
edavalosanaya/FastPoseCNN mentioned on GitHubpytorchMITSyntology: 5 samples, 5 ran (0 instrument-failed) · 0 unverified report
interactivegl/vision6d mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
lh641446825/NOCS_2019CVPR mentioned on GitHubtfSyntology: not harvested report
pairlab/6pack mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 6-PACK: Category-level 6D Pose Tracker with Anchor-Based Keypoints (arXiv:1910.10750; that paper's own run record: 15 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
sahithchada/NOCS_PyTorch mentioned on GitHubpytorchMITSyntology: 15 samples, 13 ran (2 instrument-failed) · 2 unverified report
ykzzyk/vision6d mentioned on GitHubGPL-3.0Syntology: not harvested report
wenbowen123/BundleTrack pytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to You Only Demonstrate Once: Category-Level Manipulation from Single Visual Demonstration (arXiv:2201.12716; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 1 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 12 unverified); nothing checks that they implement this paper's method. report
zubair-irshad/CenterSnap pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization (arXiv:2207.13691; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 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

20 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 1 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
15ran
2unverified

Licence: 0 of the 20 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

edavalosanaya/FastPoseCNN community (archive-listed) 5 samples, 5 ran (0 instrument-failed) · 0 unverified
cartesian_2_homogeneous_coord source_code/FastPoseCNN/lib/gpu_tensor_funcs.py ran fingerprinted MIT (permissive) · 9155d097d86fdf48 · report fixture: signature cartesian_coord:Tensor/2/float · returned Tensor · level recorded 2026-09-26
compress_dict source_code/FastPoseCNN/lib/pose_regressor.py ran MIT (permissive) · 39a6b29e494e3854 · report fixture: signature my_dict:dict/0/?, additional_subkey:str/0/str · returned dict · level recorded 2026-09-26
dec_empty_check source_code/FastPoseCNN/lib/loss.py ran MIT (permissive) · 8a8f9ac29ee2f0f9 · report fixture: signature function:callable/0/? · returned function · level recorded 2026-09-26
get_standard_preds source_code/FastPoseCNN/lib/matching.py ran MIT (permissive) · e7de4517508fd1cc · report fixture: signature gts:dict/0/?, n_of_data:int/0/int · returned dict · level recorded 2026-09-26
normalize in 638 papers
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket
source_code/FastPoseCNN/lib/gpu_tensor_funcs.py ran fingerprinted MIT (permissive) · 9e55c8fa32330a06 · report fixture: signature data:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-26
sahithchada/NOCS_PyTorch community (archive-listed) 15 samples, 13 ran (2 instrument-failed) · 2 unverified
apply_mask in 25 papers visualize.py ran MIT (permissive) · cdda836085a5b1af · report fixture: signature image:ndarray/3/float, mask:ndarray/2/int, color:ndarray/1/float, alpha:float/0/float · returned ndarray · level recorded 2026-09-24
compute_iou in 68 papers utils.py ran MIT (permissive) · b2aae18de5fa3893 · report fixture: signature box:ndarray/1/float, boxes:ndarray/2/float, box_area:float/0/float, boxes_area:ndarray/1/float · returned ndarray · level recorded 2026-09-25
compute_overlaps in 11 papers utils.py ran fingerprinted MIT (permissive) · 698f3241ee39ad75 · report fixture: signature boxes1:ndarray/2/float, boxes2:ndarray/2/float · returned ndarray · level recorded 2026-09-25
crop_and_resize in 11 papers model.py ran MIT (permissive) · 69c7643b22386435 · report fixture: signature image:Tensor/4/float, boxes:Tensor/2/float, box_indices:Tensor/1/int, crop_size:tuple/1/int · returned Tensor · level recorded 2026-09-24
draw_box in 16 papers visualize.py ran · our draft was wrong MIT (permissive) · dc05d22f3d39bea6 · report fixture: signature image:ndarray/3/int, box:tuple/1/int, color:list/1/int · returned ndarray · level recorded 2026-09-24
estimateRestrictedAffineTransform aligning.py ran MIT (permissive) · e8287b383349ddf6 · report fixture: signature source:ndarray/2/float, target:ndarray/2/float, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24
estimateSimilarityTransform aligning.py ran MIT (permissive) · b7f7231e07daadeb · report fixture: signature source:ndarray/2/float, target:ndarray/2/float, verbose:bool/0/bool · returned tuple · level recorded 2026-09-24
extract_bboxes in 14 papers utils.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d2c9b72e23d9588a · report fixture: signature mask:ndarray/3/int · returned ndarray · level recorded 2026-09-24
getRANSACInliers aligning.py ran MIT (permissive) · 4f2d0da31c4fd316 · report fixture: signature SourceHom:ndarray/2/float, TargetHom:ndarray/2/float, MaxIterations:int/0/int, PassThreshold:int/0/int, StopThreshold:int/0/int · returned tuple · level recorded 2026-09-24
intersect1d model.py ran fingerprinted MIT (permissive) · 555b5a67f9b65e14 · report fixture: signature tensor1:Tensor/1/int, tensor2:Tensor/1/int · returned Tensor · level recorded 2026-09-24
nocs_map_rotation loss.py ran MIT (permissive) · 0466b12c0859f1a9 · report fixture: signature positive_class_ids:Tensor/1/int, positive_ix:Tensor/1/int, target_coords:Tensor/4/float, mask_shape:tuple/1/int · returned tuple · level recorded 2026-09-26
random_colors in 12 papers visualize.py ran · honoured contract MIT (permissive) · a9d0cf3b71fefa32 · report fixture: signature N:int/0/int, bright:bool/0/bool · returned list · level recorded 2026-09-24
unique1d model.py ran fingerprinted MIT (permissive) · 5866d898668b0ddc · report fixture: signature tensor:Tensor/1/float · returned Tensor · level recorded 2026-09-24
compute_losses in 9 papers loss.py unverified MIT (permissive) · b73499f3de89c7b5 · report
compute_mrcnn_coord_bins_symmetry_loss loss.py unverified MIT (permissive) · a0c70f26b59ee20f · report

Tasks

6D Pose Estimation6D Pose Estimation using RGBMixed RealityObjectPose Estimation

Datasets

Introduced by this paper, per the archive.

REAL275

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
6D Pose Estimation using RGBD CAMERA25 NOCS (128 bins) mAP 10, 10cm 62.2 #2 of 2 Archive leaderboard report
6D Pose Estimation using RGBD CAMERA25 NOCS (128 bins) mAP 10, 5cm 61.7 #2 of 2 Archive leaderboard report
6D Pose Estimation using RGBD CAMERA25 NOCS (128 bins) mAP 3DIou@25 91.4 #2 of 2 Archive leaderboard report
6D Pose Estimation using RGBD CAMERA25 NOCS (128 bins) mAP 3DIou@50 85.3 #2 of 2 Archive leaderboard report
6D Pose Estimation using RGBD CAMERA25 NOCS (128 bins) mAP 5, 5cm 38.8 #2 of 2 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 NOCS (128 bins) mAP 10, 10cm 26.7 #9 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 NOCS (128 bins) mAP 10, 5cm 26.7 #9 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 NOCS (128 bins) mAP 3DIou@25 84.9 #9 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 NOCS (128 bins) mAP 3DIou@50 80.5 #9 of 11 Archive leaderboard report
6D Pose Estimation using RGBD REAL275 NOCS (128 bins) mAP 5, 5cm 9.5 #9 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.

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