Papers › Robustifying Point Cloud Networks by Refocusing

Robustifying Point Cloud Networks by Refocusing

10 Aug 2023arXiv:2308.05525archive 2025-07-28

Meir Yossef Levi, Guy Gilboa

The ability to cope with out-of-distribution (OOD) corruptions and adversarial attacks is crucial in real-world safety-demanding applications. In this study, we develop a general mechanism to increase neural network robustness based on focus analysis. Recent studies have revealed the phenomenon of Overfocusing, which leads to a performance drop. When the network is primarily influenced by small input regions, it becomes less robust and prone to misclassify under noise and corruptions. However, quantifying overfocusing is still vague and lacks clear definitions. Here, we provide a mathematical definition of focus, overfocusing and underfocusing. The notions are general, but in this study, we specifically investigate the case of 3D point clouds. We observe that corrupted sets result in a biased focus distribution compared to the clean training set. We show that as focus distribution deviates from the one learned in the training phase - classification performance deteriorates. We thus propose a parameter-free refocusing algorithm that aims to unify all corruptions under the same distribution. We validate our findings on a 3D zero-shot classification task, achieving SOTA in robust 3D classification on ModelNet-C dataset, and in adversarial defense against Shape-Invariant attack. Code is available in: https://github.com/yossilevii100/refocusing.

PaperPDFCodeCode 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 22 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 2 repositories, 16 ran (11 with no instrument failure; 5 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yossilevii100/critical_points2 officialmentioned in papermentioned on GitHubpytorchSyntology: 19 samples, 14 ran (5 instrument-failed) · 5 unverified report
yossilevii100/refocusing officialmentioned in paperpytorchSyntology: 3 samples, 2 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

22 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 6 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.

2ran · honoured contract
1ran · violated contract
2ran · our draft was wrong
3ran; the contract check could not run
8ran
6unverified

Licence: 22 of the 22 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.

yossilevii100/critical_points2 official repository 19 samples, 14 ran (5 instrument-failed) · 5 unverified
build_shared_mlp in 7 papers pointnet2_ops_lib/pointnet2_ops/pointnet2_modules.py ran; the contract check could not run (RAISES) no licence file found · pointer only · c80f9bbb31e6cb9f · report fixture: signature mlp_spec:list/1/int, bn:bool/0/bool · returned Sequential · level recorded 2026-09-22
closest_pool in 7 papers shape_invariant_attack/model_utils/kpconv_util.py ran · our draft was wrong no licence file found · pointer only · 728888ce9772c062 · report fixture: signature x:Tensor/2/float, inds:Tensor/2/int · returned Tensor · level recorded 2026-09-24
farthest_point_sample in 64 papers shape_invariant_attack/data_utils/ModelNetDataLoader.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f80066a00e7156a2 · report fixture: signature point:ndarray/2/float, npoint:int/0/int · returned ndarray · level recorded 2026-09-25
gather in 75 papers shape_invariant_attack/model_utils/kpconv_util.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 06eb9b038422a6ef · report fixture: signature x:Tensor/3/float, idx:Tensor/2/int, method:int/0/int · returned Tensor · level recorded 2026-09-22
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
shape_invariant_attack/model_utils/curvenet_util.py ran fingerprinted no licence file found · pointer only · fd43b3106ac73716 · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
shape_invariant_attack/model_utils/GDANet_util.py ran fingerprinted no licence file found · pointer only · 00b9b0b222ab4b4a · report fixture: signature x:Tensor/3/float, k:int/0/int · returned tuple · level recorded 2026-09-24
load_h5 in 10 papers robust_classification/modelnetc_utils/dataset.py ran no licence file found · pointer only · 1bfbbe6bae6f8e29 · report fixture: signature h5_name:str/0/str · returned tuple · level recorded 2026-09-24
local_operator shape_invariant_attack/model_utils/GDANet_util.py ran fingerprinted no licence file found · pointer only · 3f12c1601dd3359b · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
local_operator_withnorm shape_invariant_attack/model_utils/GDANet_util.py ran no licence file found · pointer only · 6ed05ef701fbeb72 · report fixture: signature x:Tensor/3/float, norm_plt:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
normal_knn shape_invariant_attack/model_utils/curvenet_util.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 1979f86a5b2b0446 · report fixture: signature x:Tensor/3/float, k:int/0/int · returned Tensor · level recorded 2026-09-24
pc_normalize in 81 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
shape_invariant_attack/data_utils/ModelNetDataLoader.py ran · honoured contract fingerprinted no licence file found · pointer only · 4783fbece52f500e · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-22
pc_normalize in 81 papers
census: 2 implementations from 6 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
shape_invariant_attack/model_utils/curvenet_util.py ran · honoured contract fingerprinted no licence file found · pointer only · ec413739d406e611 · report fixture: signature pc:ndarray/2/float · returned ndarray · level recorded 2026-09-22
radius_gaussian in 11 papers shape_invariant_attack/model_utils/kpconv_util.py ran · violated contract no licence file found · pointer only · 42f2cd40ba483d3b · report fixture: signature sq_r:Tensor/3/float, sig:Tensor/2/float, eps:float/0/float · returned Tensor · level recorded 2026-09-22
translate_pointcloud in 15 papers robust_classification/data.py ran fingerprinted no licence file found · pointer only · 66c3dd8b246f27ea · report fixture: signature pointcloud:ndarray/2/float · returned ndarray · level recorded 2026-09-24
assign_score_withk shape_invariant_attack/cuda_lib/functional.py unverified no licence file found · pointer only · 72e38b49e5bad8ba · report
assign_score_withk_halfkernel shape_invariant_attack/cuda_lib/functional.py unverified no licence file found · pointer only · f6e6c6c45d23680a · report
extract_importance shape_invariant_attack/baselines/defense/critical_points/critical_points.py unverified no licence file found · pointer only · cb665ba9b96a8225 · report
load_data in 700 papers robust_classification/data.py unverified no licence file found · pointer only · 551f80023618dce7 · report
my_entropy shape_invariant_attack/baselines/defense/critical_points/critical_points.py unverified no licence file found · pointer only · 2020ce134161e8a3 · report
yossilevii100/refocusing official repository 3 samples, 2 ran (0 instrument-failed) · 1 unverified
get_scorenet_input shape_invariant_attack/model_utils/paconv_util.py ran no licence file found · pointer only · d77f00230e16006d · report fixture: signature x:Tensor/3/float, idx:Tensor/3/int, k:int/0/int · returned Tensor · level recorded 2026-09-24
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
shape_invariant_attack/model_utils/paconv_util.py ran fingerprinted no licence file found · pointer only · 69845e3c207ea9e7 · report fixture: signature x:Tensor/3/float, k:int/0/int · returned tuple · level recorded 2026-09-24
feat_trans_dgcnn shape_invariant_attack/model_utils/paconv_util.py unverified no licence file found · pointer only · 5fb9a68241c62149 · report

Tasks

3D ClassificationAdversarial DefensePoint Cloud ClassificationRobust classificationZero-Shot Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Point Cloud Classification PointCloud-C Critical Points++&EPiC(RPC) mean Corruption Error (mCE) 0.476 #2 of 24 Archive leaderboard report
Point Cloud Classification PointCloud-C Critical Points++&EPiC(DGCNN) mean Corruption Error (mCE) 0.484 #3 of 24 Archive leaderboard report
Point Cloud Classification PointCloud-C Critical Points++&EPiC(GDANet) mean Corruption Error (mCE) 0.493 #4 of 24 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

Focus

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