Papers › Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding

Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding

4 Dec 2023CVPR 2024 1arXiv:2312.02244archive 2025-07-28

Guofeng Mei, Luigi Riz, Yiming Wang, Fabio Poiesi

Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs). Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking the inherent and expressible point cloud geometric structure. Geometrically similar or close regions can be exploited for bolstering point cloud understanding as they are likely to share semantic information. To this end, we introduce the first training-free aggregation technique that leverages the point cloud's 3D geometric structure to improve the quality of the transferred Vision-Language Models. Our approach operates iteratively, performing local-to-global aggregation based on geometric and semantic point-level reasoning. We benchmark our approach on three downstream tasks, including classification, part segmentation, and semantic segmentation, with a variety of datasets representing both synthetic/real-world, and indoor/outdoor scenarios. Our approach achieves new state-of-the-art results in all benchmarks. Our approach operates iteratively, performing local-to-global aggregation based on geometric and semantic point-level reasoning. Code and dataset are available at https://luigiriz.github.io/geoze-website/

PaperPDFConference PDFCodeCode 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="2312.02244")

Code

Syntology Ran 16 of 20 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 16 ran with no contract checked.

By repository: official repository: 20 samples from 1 repository, 16 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gfmei/GeoZe officialmentioned 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

20 samples harvested; 16 ran; 0 honoured the contract we drafted; 4 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.

16ran
4unverified

Licence: 20 of the 20 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 gfmei/GeoZe. “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.

batched_eigh gfmei/GeoZe/demo/semgeozev2.py official repository ran fingerprinted no licence file found · pointer only · 0ddc9c4e7df97794 · report
fps_seed gfmei/GeoZe/partseg/simple_geoze.py official repository ran fingerprinted no licence file found · pointer only · 7381bad7592335aa · report
gather_nb gfmei/GeoZe/common/pointops.py official repository ran no licence file found · pointer only · 19852a1ff2fd9ab2 · report
gather_s gfmei/GeoZe/common/pointops.py official repository ran no licence file found · pointer only · 37de6e910e12893c · report
gmm_params gfmei/GeoZe/libs/lib_clust.py official repository ran no licence file found · pointer only · b81cab32fa63d0ee · report
kmeans gfmei/GeoZe/partseg/simple_geoze.py official repository ran no licence file found · pointer only · c72e0cca85e9493f · report
knn gfmei/GeoZe/common/pointops.py official repository ran fingerprinted no licence file found · pointer only · 16259320ec4953bd · report
load_class gfmei/GeoZe/partseg/shapenet.py official repository ran no licence file found · pointer only · 428587a67c8dfbdd · report
max_flow gfmei/GeoZe/common/maxflow.py official repository ran no licence file found · pointer only · 3ed970bbd58c4bf2 · report
mesh_superpoints gfmei/GeoZe/semseg/scannet.py official repository ran no licence file found · pointer only · 80e5d23b7495f410 · report
scene_list gfmei/GeoZe/semseg/scannet.py official repository ran no licence file found · pointer only · 9431e4940ea4cfad · report
section gfmei/GeoZe/demo/pack_space.py official repository ran fingerprinted no licence file found · pointer only · c2a45790e999a42d · report
seg_mean gfmei/GeoZe/demo/semgeozev2.py official repository ran no licence file found · pointer only · eb7188d454e406e1 · report
seg_normal gfmei/GeoZe/demo/semgeozev2.py official repository ran no licence file found · pointer only · e810148c41214b3a · report
strip gfmei/GeoZe/demo/pack_space.py official repository ran fingerprinted no licence file found · pointer only · 7068111dba64f0a3 · report
voxel_keep gfmei/GeoZe/demo/pack_space_data.py official repository ran no licence file found · pointer only · c7b7a048f9b3aa0e · report
load_data_partseg gfmei/GeoZe/partseg/shapenet.py official repository unverified no licence file found · pointer only · b0c2d0fc049414fd · report
load_data_partseg_local gfmei/GeoZe/partseg/shapenet.py official repository unverified no licence file found · pointer only · be9ae20c0a2f19b2 · report
pairwise_histogram_distance_pytorch gfmei/GeoZe/libs/lib_clust.py official repository unverified no licence file found · pointer only · 49325bff6cec62f4 · report
read gfmei/GeoZe/demo/pack_space.py official repository unverified no licence file found · pointer only · 2b8321b24e059be4 · report

Tasks

SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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