Papers › IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation

IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation

23 Mar 2023ICCV 2023 1arXiv:2303.13479archive 2025-07-28

Jianhui Liu, Yukang Chen, Xiaoqing Ye, Xiaojuan Qi

Category-level 6D pose estimation aims to predict the poses and sizes of unseen objects from a specific category. Thanks to prior deformation, which explicitly adapts a category-specific 3D prior (i.e., a 3D template) to a given object instance, prior-based methods attained great success and have become a major research stream. However, obtaining category-specific priors requires collecting a large amount of 3D models, which is labor-consuming and often not accessible in practice. This motivates us to investigate whether priors are necessary to make prior-based methods effective. Our empirical study shows that the 3D prior itself is not the credit to the high performance. The keypoint actually is the explicit deformation process, which aligns camera and world coordinates supervised by world-space 3D models (also called canonical space). Inspired by these observations, we introduce a simple prior-free implicit space transformation network, namely IST-Net, to transform camera-space features to world-space counterparts and build correspondence between them in an implicit manner without relying on 3D priors. Besides, we design camera- and world-space enhancers to enrich the features with pose-sensitive information and geometrical constraints, respectively. Albeit simple, IST-Net achieves state-of-the-art performance based-on prior-free design, with top inference speed on the REAL275 benchmark. Our code and models are available at https://github.com/CVMI-Lab/IST-Net.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 17 code samples harvested from 1 repository linked to this paper: 10 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 10 ran (7 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

cvmi-lab/ist-net officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 10 ran (3 instrument-failed) · 7 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

17 samples harvested: 10 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 7 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.

3ran · our draft was wrong
7ran
7unverified

Licence: 0 of the 17 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 cvmi-lab/ist-net. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

cvmi-lab/ist-net official repository 17 samples, 10 ran (3 instrument-failed) · 7 unverified
FeatureDeformer model/ist_net.py ran · metamorphic tier: deterministic MIT (permissive) · 818784846051f432 · report fixture: returned FeatureDeformer · level recorded 2026-09-22
HeavyEstimator model/ist_net.py ran fingerprinted MIT (permissive) · 3bd973fd8cb0caea · report fixture: signature pts:Tensor/3/float, pts_w:Tensor/3/float, rgb_local:Tensor/3/float, pts_local:Tensor/3/float, pts_w_local:Tensor/3/float · returned tuple · level recorded 2026-09-24
ImplicitTransformation model/ist_net.py ran · metamorphic tier: deterministic MIT (permissive) · 1d559539b5fd17e2 · report fixture: returned ImplicitTransformation · level recorded 2026-09-22
LightEstimator model/ist_net.py ran MIT (permissive) · aa0312fa44827865 · report fixture: signature pts:Tensor/3/float, rgb_local:Tensor/3/float, pts_local:Tensor/3/float · returned tuple · level recorded 2026-09-24
Ortho6d2Mat model/ist_net.py ran · our draft was wrong MIT (permissive) · 1daaf09e602222b1 · report fixture: returned Tensor · level recorded 2026-09-22
PSPModule model/ist_net.py ran · metamorphic tier: deterministic MIT (permissive) · cb91f44199de6c8a · report fixture: returned PSPModule · level recorded 2026-09-22
PSPUpsample model/ist_net.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 140d1a79031a84e8 · report fixture: returned PSPUpsample · level recorded 2026-09-22
PointnetFPModule in 8 papers model/ist_net.py ran · metamorphic tier: deterministic MIT (permissive) · 29b15b0b306bea32 · report fixture: returned PointnetFPModule · level recorded 2026-09-22
cross_product in 7 papers model/ist_net.py ran · our draft was wrong fingerprinted MIT (permissive) · b3e34851c4bae3c3 · report fixture: signature u:Tensor/2/float, v:Tensor/2/float · returned Tensor · level recorded 2026-09-22
normalize_vector in 17 papers
census: 6 implementations from 7 papers, 3 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
model/ist_net.py ran · our draft was wrong MIT (permissive) · 6fb9de09c860abe9 · report fixture: returned Tensor · level recorded 2026-09-22
IST_Net model/ist_net.py unverified MIT (permissive) · 17385d6868dc70e1 · report
ModifiedResnet model/ist_net.py unverified MIT (permissive) · be642c1b9268c6d7 · report
Modified_PSPNet model/ist_net.py unverified MIT (permissive) · 9d39a71cb84d79f1 · report
PointNet2MSG model/ist_net.py unverified MIT (permissive) · 5586282a82daf188 · report
PointnetSAModuleMSG in 9 papers model/ist_net.py unverified MIT (permissive) · e2b1301d9768573d · report
WorldSpaceEnhancer model/ist_net.py unverified MIT (permissive) · 6236f9a78c48ef46 · report
_PointnetSAModuleBase in 8 papers model/ist_net.py unverified MIT (permissive) · 1b50e7cbedb8823e · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for IST-Net (graph method: IST-Net). 30 bricks; individually on a fixture: 22 ran (of which 17 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. IST_Net entry · level 0 · unverified · 17385d6868dc70e1
  2. HeavyEstimator model · level 1 · ran · 3bd973fd8cb0caea
  3. ImplicitTransformation model · level 1 · ran · 1d559539b5fd17e2
  4. LightEstimator model · level 1 · ran · aa0312fa44827865
  5. ModifiedResnet model · level 0 · unverified · be642c1b9268c6d7
  6. PointNet2MSG helper · level 0 · unverified · 5586282a82daf188
  7. WorldSpaceEnhancer model · level 0 · unverified · 6236f9a78c48ef46
  8. Ortho6d2Mat helper · level 1 · ran · our draft was wrong · 1daaf09e602222b1
  9. FeatureDeformer helper · level 1 · ran · 818784846051f432
  10. PointnetFPModule helper · level 1 · ran · 29b15b0b306bea32
  11. PointnetSAModuleMSG helper · level 0 · unverified · e2b1301d9768573d
  12. cross_product helper · level 1 · ran · our draft was wrong · b3e34851c4bae3c3
  13. normalize_vector helper · level 1 · ran · our draft was wrong · 6fb9de09c860abe9
  14. SharedMLP helper · level 1 · ran · dbd9c5b5bde4b57b
  15. GroupAll helper · level 1 · ran · 445cffa437113b80
  16. QueryAndGroup helper · level 0 · unverified · 5d1e43f12483593d
  17. _PointnetSAModuleBase helper · level 0 · unverified · 1b50e7cbedb8823e
  18. Conv2d helper · level 1 · ran · 13cd8bfa92565fb3
  19. BatchNorm2d helper · level 1 · ran · ea90589983c7d4fb
  20. _ConvBase helper · level 1 · ran · 37537db27757694f
  21. _BNBase helper · level 1 · ran · 359fcb0c4f682234
  22. BallQuery helper · level 1 · ran · fdd72fc42b06427f
  23. FurthestPointSampling helper · level 1 · ran · 018e0e61ae702455
  24. GatherOperation helper · level 1 · ran · 3c75be14968690dc
  25. GroupingOperation helper · level 1 · ran · 4d80a2b4a0fba485
  26. Modified_PSPNet helper · level 0 · unverified · 9d39a71cb84d79f1
  27. PSPModule helper · level 1 · ran · cb91f44199de6c8a
  28. PSPUpsample helper · level 1 · ran · 140d1a79031a84e8
  29. ThreeInterpolate helper · level 1 · ran · 565863bfed9f02fc
  30. ThreeNN helper · level 1 · ran · 11f8d19732aa2254

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2303.13479") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

6D Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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