Papers › AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds

AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds

12 Aug 2021ICCV 2021 10arXiv:2108.05836archive 2025-07-28

Runsong Zhu, YuAn Liu, Zhen Dong, Tengping Jiang, YuAn Wang, Wenping Wang, Bisheng Yang

This paper presents a neural network for robust normal estimation on point clouds, named AdaFit, that can deal with point clouds with noise and density variations. Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has difficulty in finding accurate normals in complex regions or containing noisy points. By analyzing the step of weighted least squares surface fitting, we find that it is hard to determine the polynomial order of the fitting surface and the fitting surface is sensitive to outliers. To address these problems, we propose a simple yet effective solution that adds an additional offset prediction to improve the quality of normal estimation. Furthermore, in order to take advantage of points from different neighborhood sizes, a novel Cascaded Scale Aggregation layer is proposed to help the network predict more accurate point-wise offsets and weights. Extensive experiments demonstrate that AdaFit achieves state-of-the-art performance on both the synthetic PCPNet dataset and the real-word SceneNN dataset.

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: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 17 samples from 1 repository, 9 ran (5 with no instrument failure; 4 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

runsong123/adafit officialmentioned in papermentioned on GitHubpytorchSyntology: 17 samples, 9 ran (4 instrument-failed) · 8 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: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 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.

2ran · our draft was wrong
2ran; the contract check could not run
5ran
8unverified

Licence: 17 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 runsong123/adafit. “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 2 samples 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.

runsong123/adafit official repository 17 samples, 9 ran (4 instrument-failed) · 8 unverified
BaseBC models/AdaFit_multi_scale.py ran no licence file found · pointer only · c84070aee408732d · report fixture: returned BaseBC · level recorded 2026-09-22
BaseBF models/AdaFit_multi_scale.py ran no licence file found · pointer only · 0da3abc050b0a66b · report fixture: returned BaseBF · level recorded 2026-09-22
Inception3D models/AdaFit_multi_scale.py ran no licence file found · pointer only · 8834f32b69b83af3 · report fixture: returned Inception3D · level recorded 2026-09-22
STN models/AdaFit_multi_scale.py ran no licence file found · pointer only · b2bb9a5d3998694c · report fixture: returned STN · level recorded 2026-09-22
VariableScaleLayer models/AdaFit_multi_scale.py ran no licence file found · pointer only · abe6fbe3f2dcc072 · report fixture: returned VariableScaleLayer · level recorded 2026-09-22
batch_quat_to_rotmat models/AdaFit_multi_scale.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 8e631a5d06b64765 · report fixture: signature q:Tensor/2/float, out:NoneType/0/? · returned Tensor · level recorded 2026-09-22
fit_Wjet models/AdaFit_multi_scale.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 9e8d607f21afdb0f · report fixture: signature points:Tensor/3/float, weights:Tensor/2/float, order:int/0/int, compute_neighbor_normals:bool/0/bool · returned tuple · level recorded 2026-09-22
get_3DmFV_pytorch models/AdaFit_multi_scale.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · ecb295a64a2d0737 · report fixture: signature points:Tensor/3/float, w:ndarray/1/float, mu:ndarray/2/float, sigma:ndarray/2/float, normalize:bool/0/bool · returned Tensor · level recorded 2026-09-22
solve_linear_system in 7 papers models/AdaFit_multi_scale.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cf1d6127981c7181 · report fixture: signature XtX:Tensor/3/float, XtY:Tensor/3/float, sub_batch_size:int/0/int · returned Tensor · level recorded 2026-09-22
DeepFit models/AdaFit_multi_scale.py unverified no licence file found · pointer only · ba8dc700dee0518a · report
Global3DmFVFeature models/AdaFit_multi_scale.py unverified no licence file found · pointer only · 02c419a41377302d · report
PointNet3DmFVEncoder models/AdaFit_multi_scale.py unverified no licence file found · pointer only · 75e4c5399e922c27 · report
PointNetEncoder models/AdaFit_multi_scale.py unverified no licence file found · pointer only · 2869c04723232e53 · report
PointNetFeatures models/AdaFit_multi_scale.py unverified no licence file found · pointer only · b98d64954f74d799 · report
QSTN models/AdaFit_multi_scale.py unverified no licence file found · pointer only · ae6834ddb339bc38 · report
ThreeDmFVNet models/AdaFit_multi_scale.py unverified no licence file found · pointer only · 48d97aea48dac671 · report
get_3d_grid_gmm models/AdaFit_multi_scale.py unverified no licence file found · pointer only · 9144350149cc9475 · 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 AdaFit (graph method: AdaFit). 17 bricks; individually on a fixture: 9 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. DeepFit entry · level 0 · unverified · ba8dc700dee0518a
  2. PointNet3DmFVEncoder helper · level 0 · unverified · 75e4c5399e922c27
  3. PointNetEncoder helper · level 0 · unverified · 2869c04723232e53
  4. fit_Wjet helper · level 1 · ran; the contract check could not run (RAISES) · 9e8d607f21afdb0f
  5. PointNetFeatures model · level 0 · unverified · b98d64954f74d799
  6. ThreeDmFVNet helper · level 0 · unverified · 48d97aea48dac671
  7. get_3DmFV_pytorch helper · level 1 · ran; the contract check could not run (RAISES) · ecb295a64a2d0737
  8. get_3d_grid_gmm helper · level 0 · unverified · 9144350149cc9475
  9. VariableScaleLayer model · level 1 · ran · abe6fbe3f2dcc072
  10. solve_linear_system helper · level 1 · ran · our draft was wrong · cf1d6127981c7181
  11. QSTN helper · level 0 · unverified · ae6834ddb339bc38
  12. STN helper · level 1 · ran · b2bb9a5d3998694c
  13. Global3DmFVFeature helper · level 0 · unverified · 02c419a41377302d
  14. BaseBC helper · level 1 · ran · c84070aee408732d
  15. BaseBF helper · level 1 · ran · 0da3abc050b0a66b
  16. batch_quat_to_rotmat helper · level 1 · ran · our draft was wrong · 8e631a5d06b64765
  17. Inception3D helper · level 1 · ran · 8834f32b69b83af3

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="2108.05836") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Surface Normals Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Surface Normals Estimation PCPNet AdaFit RMSE 10.76 #5 of 8 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