Papers › ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes

ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes

19 Jan 2022CVPR 2022 1arXiv:2201.07788archive 2025-07-28

Rahul Sajnani, Adrien Poulenard, Jivitesh Jain, Radhika Dua, Leonidas J. Guibas, Srinath Sridhar

Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose). This has made it hard to generalize these methods to in-the-wild shapes, eg., from internet model collections or depth sensors. ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds. We build on top of Tensor Field Networks (TFNs), a class of permutation- and rotation-equivariant, and translation-invariant 3D networks. During inference, our method takes an unseen full or partial 3D point cloud at an arbitrary pose and outputs an equivariant canonical pose. During training, this network uses self-supervision losses to learn the canonical pose from an un-canonicalized collection of full and partial 3D point clouds. ConDor can also learn to consistently co-segment object parts without any supervision. Extensive quantitative results on four new metrics show that our approach outperforms existing methods while enabling new applications such as operation on depth images and annotation transfer.

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 19 code samples harvested from 1 repository linked to this paper: 18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 19 samples from 1 repository, 18 ran (18 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

brown-ivl/ConDor officialtfMITSyntology: 19 samples, 18 ran (0 instrument-failed) · 1 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

19 samples harvested: 18 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

18ran
1unverified

Licence: 0 of the 19 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 brown-ivl/ConDor. “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.

brown-ivl/ConDor official repository 19 samples, 18 ran (0 instrument-failed) · 1 unverified
apply_mlp ConDor/auto_encoder/tfn_atlasnet.py ran MIT (permissive) · a43929f6265ac2c2 · report fixture: signature x:EagerTensor/2/float, mlp:list/1/dict · returned EagerTensor · level recorded 2026-09-24
eqvar_heads_fuzion ConDor/network_utils/convolution.py ran MIT (permissive) · 95ec15b1571be826 · report fixture: signature X:list/1/dict · returned dict · level recorded 2026-09-24
grid_sampler ConDor/network_utils/pooling.py ran MIT (permissive) · 183d074ff7b98277 · report fixture: signature x:EagerTensor/3/float, cell_size:float/0/float, num_points_target:int/0/int · returned tuple · level recorded 2026-09-24
grid_sampler_ ConDor/network_utils/pooling.py ran MIT (permissive) · 87f376a5a795f16c · report fixture: returned tuple · level recorded 2026-09-24
mask in 19 papers ConDor/network_utils/convolution.py ran MIT (permissive) · 8b561ee6fdb8f3fd · report fixture: signature x:dict/0/?, mask:EagerTensor/2/float · returned dict · level recorded 2026-09-24
norml2 ConDor/network_utils/activations.py ran MIT (permissive) · 83c97d74407b4755 · report fixture: signature x:EagerTensor/2/float, axis:int/0/int, keepdims:bool/0/bool, eps:float/0/float · returned EagerTensor · level recorded 2026-09-24
patches_radius ConDor/network_utils/group_points.py ran MIT (permissive) · c01f0222f247ed28 · report fixture: signature radius:float/0/float, sq_norm:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
set_mlp ConDor/auto_encoder/tfn_atlasnet.py ran MIT (permissive) · f1475b36486b7bbe · report fixture: signature units:list/1/int, momentum:float/0/float · returned list · level recorded 2026-09-24
set_sphere_weights ConDor/auto_encoder/tfn_atlasnet.py ran MIT (permissive) · 34d3cd3a8304196e · report fixture: signature units:int/0/int, types:list/1/int · returned dict · level recorded 2026-09-24
sq_dist_mat ConDor/evaluators/train_pointnet_cls2.py ran MIT (permissive) · bc0a1952c0374318 · report fixture: signature x:EagerTensor/3/float, y:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
squash in 30 papers
census: 8 implementations from 5 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
ConDor/network_utils/activations.py ran MIT (permissive) · 6ee731af0229a9ba · report fixture: signature x:EagerTensor/3/float, b:float/0/float, eps:float/0/float, bias:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-24
std in 5 papers ConDor/evaluators/train_pointnet_cls2.py ran MIT (permissive) · 95a1e02c41de556a · report fixture: signature x:EagerTensor/2/float, axis_mean:int/0/int, axis_norm:int/0/int · returned tuple · level recorded 2026-09-24
tf_heaviside ConDor/network_utils/sh_conv.py ran MIT (permissive) · 492443ff0f1a5a31 · report fixture: signature X:SymbolicTensor/2/float · returned EagerTensor · level recorded 2026-09-24
tf_segment_indicator_ ConDor/network_utils/sh_conv.py ran MIT (permissive) · b7f5b304241048ea · report fixture: signature X:EagerTensor/2/float, a:EagerTensor/0/float, b:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-24
tf_segment_indictor ConDor/network_utils/sh_conv.py ran MIT (permissive) · 645fc9c3ed7714e6 · report fixture: signature X:EagerTensor/2/float, r:EagerTensor/0/float, sigma:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-24
tf_unique_with_inverse ConDor/network_utils/group_points.py ran MIT (permissive) · cb175242ae058123 · report fixture: signature x:EagerTensor/1/int · returned tuple · level recorded 2026-09-24
tf_unique_with_inverse ConDor/network_utils/pooling.py ran MIT (permissive) · 30fc09c6037ff867 · report fixture: returned tuple · level recorded 2026-09-24
var in 16 papers ConDor/evaluators/train_pointnet_cls2.py ran MIT (permissive) · 9fb46aab78071109 · report fixture: signature x:EagerTensor/2/float, axis_mean:int/0/int, axis_norm:int/0/int · returned tuple · level recorded 2026-09-24
compute_patches_grid ConDor/network_utils/group_points.py unverified MIT (permissive) · 83e06b900f5f086d · report

Tasks

3D Canonicalization3D Geometry Perception3D Part Segmentation3D Pose Estimation

1 archive task tag without a task page not shown.

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