Papers › Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding

Any2Point: Empowering Any-modality Large Models for Efficient 3D Understanding

11 Apr 2024arXiv:2404.07989archive 2025-07-28

Yiwen Tang, Ray Zhang, Jiaming Liu, Zoey Guo, Dong Wang, Zhigang Wang, Bin Zhao, Shanghang Zhang, Peng Gao, Hongsheng Li, Xuelong Li

Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D domains. However, such 2D-to-3D approaches are still limited, due to the potential loss of spatial geometries and high computation cost. More importantly, their frameworks are mainly designed for 2D models, lacking a general any-to-3D paradigm. In this paper, we introduce Any2Point, a parameter-efficient method to empower any-modality large models (vision, language, audio) for 3D understanding. Given a frozen transformer from any source modality, we propose a 3D-to-any (1D or 2D) virtual projection strategy that correlates the input 3D points to the original 1D or 2D positions within the source modality. This mechanism enables us to assign each 3D token with a positional encoding paired with the pre-trained model, which avoids 3D geometry loss caused by the true projection and better motivates the transformer for 3D learning with 1D/2D positional priors. Then, within each transformer block, we insert an any-to-3D guided adapter module for parameter-efficient fine-tuning. The adapter incorporates prior spatial knowledge from the source modality to guide the local feature aggregation of 3D tokens, compelling the semantic adaption of any-modality transformers. We conduct extensive experiments to showcase the effectiveness and efficiency of our method. Code and models are released at https://github.com/Ivan-Tang-3D/Any2Point.

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

No sample from the archive's official repository (ivan-tang-3d/any2point) is linked to this paper; the 24 samples below come from 3 community repositories. Syntology harvested code from ivan-tang-3d/any2point for another paper.

ivan-tang-3d/any2point: Syntology's graph links these samples to ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and... (arXiv:2303.16894; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method.

Syntology 24 code samples harvested from 3 repositories linked to this paper: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 24 samples from 3 repositories, 17 ran (7 with no instrument failure; 10 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 17 samples that ran have no recorded date.

ivan-tang-3d/any2point officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and... (arXiv:2303.16894; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
EvenJoker/Point-PEFT mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (2 instrument-failed) · 0 unverified report
even-jk/peft-3d mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
ivan-tang-3d/peft-3d mentioned on GitHubpytorchSyntology: not harvested report
ivan-tang-3d/point-peft mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and... (arXiv:2303.16894; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ivan-tang-3d/viewrefer3d mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and... (arXiv:2303.16894; that paper's own run record: 8 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
ziyuguo99/viewrefer3d mentioned on GitHubpytorchSyntology: 18 samples, 11 ran (5 instrument-failed) · 7 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

24 samples harvested: 17 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 2 violated, 4 with no contract checked; 10 where Syntology's instrument failed) · 7 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.

1ran · honoured contract
2ran · violated contract
6ran · our draft was wrong
4ran; the contract check could not run
4ran
7unverified

Licence: 24 of the 24 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 3 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.

EvenJoker/Point-PEFT community (archive-listed) 3 samples, 3 ran (2 instrument-failed) · 0 unverified
farthest_point_sample in 64 papers M2AE/datasets/ModelNetDataset.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
load_modelnet_data in 8 papers M2AE/datasets/ModelNetDataset.py ran · our draft was wrong no licence file found · pointer only · e609e218822ed309 · report fixture: signature config:Config/0/?, partition:str/0/str · returned tuple · 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
M2AE/datasets/ModelNetDataset.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
even-jk/peft-3d community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
index_points in 49 papers M2AE/models/modules.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 449a0265144f6530 · report fixture: signature points:Tensor/3/float, idx:Tensor/2/int · returned Tensor · level recorded, date not recorded
get_activation in 218 papers M2AE/models/pointpos_st.py ran · our draft was wrong no licence file found · pointer only · 194020d4610c8bad · report fixture: signature activation:str/0/str · returned GELU · level recorded 2026-09-22
square_distance in 89 papers
census: 11 implementations from 18 papers, 4 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
M2AE/models/modules.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 3bfe172e686075cd · report fixture: signature src:Tensor/3/float, dst:Tensor/3/float · returned Tensor · level recorded, date not recorded
ziyuguo99/viewrefer3d community (archive-listed) 18 samples, 11 ran (5 instrument-failed) · 7 unverified
get_siamese_features referit3d/models/utils.py ran · our draft was wrong no licence file found · pointer only · aa2ec2ca752b21e7 · report fixture: signature net:callable/0/?, in_features:Tensor/3/float, aggregator:callable/0/? · returned Tensor · level recorded 2026-09-22
is_explicitly_view_dependent referit3d/analysis/utterances.py ran · violated contract no licence file found · pointer only · 4db1af4e710f2ed6 · report fixture: signature df:DataFrame/0/? · returned Series · level recorded 2026-09-24
load_state_dicts referit3d/models/utils.py ran no licence file found · pointer only · ca72665920bc92f3 · report fixture: signature checkpoint_file:str/0/str, map_location:NoneType/0/?, model:callable/0/? · returned int · level recorded 2026-09-24
make_batch_keys referit3d/models/referit3d_net_utils.py ran no licence file found · pointer only · c51ef25e94abe6da · report fixture: signature args:Args/0/?, extras:list/1/str · returned list · level recorded 2026-09-24
mean_color referit3d/in_out/neural_net_oriented.py ran; the contract check could not run (RAISES) no licence file found · pointer only · c231b9b5e9b289c3 · report fixture: signature scan_ids:list/1/int, all_scans:dict/0/? · returned ndarray · level recorded 2026-09-24
objects_counter_percentile referit3d/in_out/neural_net_oriented.py ran no licence file found · pointer only · d196195ea9d1c3f9 · report fixture: signature scan_ids:list/1/str, all_scans:dict/0/?, prc:int/0/int · returned float64 · level recorded 2026-09-24
read_saved_args referit3d/in_out/arguments.py ran · our draft was wrong no licence file found · pointer only · c25845a108b6da31 · report fixture: signature config_file:str/0/str, override_args:dict/0/?, verbose:bool/0/bool · returned Namespace · level recorded 2026-09-22
scan_and_target_id_to_context_info referit3d/in_out/scannet_scan.py ran no licence file found · pointer only · 8b7301dc48882200 · report fixture: signature scan_id:str/0/str, target_id:int/0/int, all_scans_in_dict:dict/0/? · returned tuple · level recorded 2026-09-24
set_bn_momentum_default in 17 papers referit3d/external_tools/pointnet2/pytorch_utils.py ran · our draft was wrong no licence file found · pointer only · 0ad12b1e8408e2f9 · report fixture: signature bn_momentum:float/0/float · returned function · level recorded 2026-09-26
subfinder referit3d/analysis/word_meanings.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 332bd8bc2636e88f · report fixture: signature mylist:list/1/int, pattern:list/1/int · returned list · level recorded 2026-09-24
uses_spatial_reasoning referit3d/analysis/word_meanings.py ran · violated contract fingerprinted no licence file found · pointer only · 05f85131bd11d076 · report fixture: signature tokens:list/1/str · returned bool · level recorded 2026-09-24
analyze_predictions referit3d/analysis/deepnet_predictions.py unverified no licence file found · pointer only · 2d4185d03e850099 · report
evaluate_on_dataset referit3d/models/referit3d_net_utils.py unverified no licence file found · pointer only · ebaea24e90c5c6a6 · report
mentions_target_class referit3d/analysis/utterances.py unverified no licence file found · pointer only · 1a538ccfac65ece4 · report
my_get_siamese_features referit3d/models/utils.py unverified no licence file found · pointer only · 7a5e6e16e707ef19 · report
parse_arguments in 61 papers referit3d/in_out/arguments.py unverified no licence file found · pointer only · 5061d20ec9e0c070 · report
scannet_official_train_val referit3d/in_out/neural_net_oriented.py unverified no licence file found · pointer only · 468cefeb0b538ad8 · report
single_epoch_train referit3d/models/referit3d_net_utils.py unverified no licence file found · pointer only · db764b929b831f74 · report

Tasks

3D geometryparameter-efficient fine-tuning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterFocus

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