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 \textit{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 \textbf{focus}, \textbf{overfocusing} and \textbf{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 \textbf{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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2308.05525")

Code

Syntology Ran 15 of 22 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 2 ran · honoured contract; 1 ran · violated contract; 2 ran · fixture could not drive it; 10 ran with no contract checked.

By repository: official repository: 22 samples from 2 repositories, 15 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

yossilevii100/critical_points2 officialmentioned in papermentioned on GitHubpytorch report
yossilevii100/refocusing officialmentioned in paperpytorch 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; 15 ran; 2 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · honoured contract
1ran · violated contract
2ran · fixture could not drive it
10ran
7unverified

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; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

build_shared_mlp yossilevii100/critical_points2/pointnet2_ops_lib/pointnet2_ops/pointnet2_modules.py official repository ran · fixture could not drive it no licence file found · pointer only · c80f9bbb31e6cb9f · report
closest_pool yossilevii100/critical_points2/shape_invariant_attack/model_utils/kpconv_util.py official repository ran no licence file found · pointer only · 728888ce9772c062 · report
gather yossilevii100/critical_points2/shape_invariant_attack/model_utils/kpconv_util.py official repository ran · fixture could not drive it no licence file found · pointer only · 06eb9b038422a6ef · report
get_scorenet_input yossilevii100/refocusing/shape_invariant_attack/model_utils/paconv_util.py official repository ran no licence file found · pointer only · d77f00230e16006d · report
knn yossilevii100/critical_points2/shape_invariant_attack/model_utils/curvenet_util.py official repository ran fingerprinted no licence file found · pointer only · fd43b3106ac73716 · report
knn yossilevii100/critical_points2/shape_invariant_attack/model_utils/GDANet_util.py official repository ran fingerprinted no licence file found · pointer only · 00b9b0b222ab4b4a · report
knn yossilevii100/refocusing/shape_invariant_attack/model_utils/paconv_util.py official repository ran fingerprinted no licence file found · pointer only · 69845e3c207ea9e7 · report
load_h5 yossilevii100/critical_points2/robust_classification/modelnetc_utils/dataset.py official repository ran no licence file found · pointer only · 1bfbbe6bae6f8e29 · report
local_operator yossilevii100/critical_points2/shape_invariant_attack/model_utils/GDANet_util.py official repository ran fingerprinted no licence file found · pointer only · 3f12c1601dd3359b · report
local_operator_withnorm yossilevii100/critical_points2/shape_invariant_attack/model_utils/GDANet_util.py official repository ran no licence file found · pointer only · 6ed05ef701fbeb72 · report
normal_knn yossilevii100/critical_points2/shape_invariant_attack/model_utils/curvenet_util.py official repository ran fingerprinted no licence file found · pointer only · 1979f86a5b2b0446 · report
pc_normalize yossilevii100/critical_points2/shape_invariant_attack/data_utils/ModelNetDataLoader.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 4783fbece52f500e · report
pc_normalize yossilevii100/critical_points2/shape_invariant_attack/model_utils/curvenet_util.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · ec413739d406e611 · report
radius_gaussian yossilevii100/critical_points2/shape_invariant_attack/model_utils/kpconv_util.py official repository ran · violated contract no licence file found · pointer only · 42f2cd40ba483d3b · report
translate_pointcloud yossilevii100/critical_points2/robust_classification/data.py official repository ran fingerprinted no licence file found · pointer only · 66c3dd8b246f27ea · report
assign_score_withk yossilevii100/critical_points2/shape_invariant_attack/cuda_lib/functional.py official repository unverified no licence file found · pointer only · 72e38b49e5bad8ba · report
assign_score_withk_halfkernel yossilevii100/critical_points2/shape_invariant_attack/cuda_lib/functional.py official repository unverified no licence file found · pointer only · f6e6c6c45d23680a · report
extract_importance yossilevii100/critical_points2/shape_invariant_attack/baselines/defense/critical_points/critical_points.py official repository unverified no licence file found · pointer only · cb665ba9b96a8225 · report
farthest_point_sample yossilevii100/critical_points2/shape_invariant_attack/data_utils/ModelNetDataLoader.py official repository unverified no licence file found · pointer only · f80066a00e7156a2 · report
feat_trans_dgcnn yossilevii100/refocusing/shape_invariant_attack/model_utils/paconv_util.py official repository unverified no licence file found · pointer only · 5fb9a68241c62149 · report
load_data yossilevii100/critical_points2/robust_classification/data.py official repository unverified no licence file found · pointer only · 551f80023618dce7 · report
my_entropy yossilevii100/critical_points2/shape_invariant_attack/baselines/defense/critical_points/critical_points.py official repository unverified no licence file found · pointer only · 2020ce134161e8a3 · 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