Papers › PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection

PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection

1 Oct 2024arXiv:2410.00320archive 2025-07-28

Qihang Zhou, Jiangtao Yan, Shibo He, Wenchao Meng, Jiming Chen

Zero-shot (ZS) 3D anomaly detection is a crucial yet unexplored field that addresses scenarios where target 3D training samples are unavailable due to practical concerns like privacy protection. This paper introduces PointAD, a novel approach that transfers the strong generalization capabilities of CLIP for recognizing 3D anomalies on unseen objects. PointAD provides a unified framework to comprehend 3D anomalies from both points and pixels. In this framework, PointAD renders 3D anomalies into multiple 2D renderings and projects them back into 3D space. To capture the generic anomaly semantics into PointAD, we propose hybrid representation learning that optimizes the learnable text prompts from 3D and 2D through auxiliary point clouds. The collaboration optimization between point and pixel representations jointly facilitates our model to grasp underlying 3D anomaly patterns, contributing to detecting and segmenting anomalies of unseen diverse 3D objects. Through the alignment of 3D and 2D space, our model can directly integrate RGB information, further enhancing the understanding of 3D anomalies in a plug-and-play manner. Extensive experiments show the superiority of PointAD in ZS 3D anomaly detection across diverse unseen objects.

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="2410.00320")

Code

Syntology Ran 17 of 26 code samples harvested from 2 repositories linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · honoured contract; 5 ran · our draft was wrong; 1 ran · fixture could not drive it; 10 ran with no contract checked.

By repository: official repository: 23 samples from 1 repository, 15 ran; community: 3 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zqhang/pointad officialmentioned in papermentioned on GitHubpytorch 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

26 samples harvested; 17 ran; 1 honoured the contract we drafted; 9 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.

1ran · honoured contract
5ran · our draft was wrong
1ran · fixture could not drive it
10ran
9unverified

Licence: 23 of the 26 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.

Attention zqhang/pointad/AnomalyCLIP_lib/AnomalyCLIP.py official repository ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 2e7ee770aa7c6018 · report
ResidualAttentionBlock_learnable_token zqhang/pointad/AnomalyCLIP_lib/AnomalyCLIP.py official repository ran · metamorphic tier: deterministic no licence file found · pointer only · b0d940f6ea95cb97 · report
basic_clean zqhang/PointAD/AnomalyCLIP_lib/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 98f385d847636a3e · report
cal_pro_score zqhang/PointAD/metrics.py official repository ran no licence file found · pointer only · 178a0488f0c59db0 · report
generate_class_info zqhang/PointAD/dataset.py official repository ran no licence file found · pointer only · 7050b3459cd4a0ff · report
generate_is_seen_for_point_in_each_view zqhang/PointAD/dataset.py official repository ran no licence file found · pointer only · 561e1516acd5b4f8 · report
get_logger zqhang/PointAD/logger.py official repository ran no licence file found · pointer only · 01e8c2f30dcaa3d3 · report
get_pairs zqhang/PointAD/AnomalyCLIP_lib/simple_tokenizer.py official repository ran · our draft was wrong no licence file found · pointer only · d919ae32e5e4e616 · report
image_level_metrics zqhang/PointAD/metrics.py official repository ran no licence file found · pointer only · fab7ecf2ea011dae · report
load_state_dict zqhang/PointAD/AnomalyCLIP_lib/model_load.py official repository ran no licence file found · pointer only · 4b3a4d17e1df3140 · report
normalize zqhang/PointAD/utils.py official repository ran · honoured contract fingerprinted no licence file found · pointer only · 0c3f9d9b0ac9f33d · report
pixel_level_metrics zqhang/PointAD/metrics.py official repository ran no licence file found · pointer only · 8652c7a523dba2e8 · report
smooth zqhang/PointAD/loss.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · abedbe9b904a9780 · report
sparsity zqhang/PointAD/loss.py official repository ran no licence file found · pointer only · 208456d9417303f4 · report
whitespace_clean zqhang/PointAD/AnomalyCLIP_lib/simple_tokenizer.py official repository ran · our draft was wrong fingerprinted no licence file found · pointer only · 9542161e9640b858 · report
AnomalyCLIP zqhang/pointad/AnomalyCLIP_lib/AnomalyCLIP.py official repository unverified no licence file found · pointer only · 3531139281d2a48e · report
ResidualAttentionBlock zqhang/pointad/AnomalyCLIP_lib/AnomalyCLIP.py official repository unverified no licence file found · pointer only · 6cbaa01bb223f295 · report
Transformer zqhang/pointad/AnomalyCLIP_lib/AnomalyCLIP.py official repository unverified no licence file found · pointer only · 904024b32ecbd1e1 · report
VisionTransformer zqhang/pointad/AnomalyCLIP_lib/AnomalyCLIP.py official repository unverified no licence file found · pointer only · f8c143f839756ff3 · report
build_model zqhang/PointAD/AnomalyCLIP_lib/build_model.py official repository unverified no licence file found · pointer only · ed57101d91ad0e4e · report
image_transform zqhang/PointAD/AnomalyCLIP_lib/transform.py official repository unverified no licence file found · pointer only · 2c38b8a1a6553df1 · report
load zqhang/PointAD/AnomalyCLIP_lib/model_load.py official repository unverified no licence file found · pointer only · 45e1ef91f571e2f5 · report
load_checkpoint zqhang/PointAD/AnomalyCLIP_lib/model_load.py official repository unverified no licence file found · pointer only · d53108edea9d2b46 · report
convert_to_custom_text_state_dict zqhang/accurate-winclip-pytorch/src/open_clip/model.py community ran · our draft was wrong MIT (permissive) · e70f60a663c06b9a · report
get_cast_dtype zqhang/accurate-winclip-pytorch/src/open_clip/model.py community ran · our draft was wrong MIT (permissive) · 1bc68318bf26bdf0 · report
build_model_from_openai_state_dict zqhang/accurate-winclip-pytorch/src/open_clip/model.py community unverified MIT (permissive) · b7bca1358293c8ab · report

Tasks

3D Anomaly DetectionAnomaly DetectionRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Anomaly Detection Real 3D-AD PointAD Mean Performance of P. and O. 0.7375 #8 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PointAD Object AUROC 0.759 #8 of 19 Archive leaderboard report
3D Anomaly Detection Real 3D-AD PointAD Point AUROC 0.716 #8 of 19 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

CLIP

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