Papers › ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point...

ConDaFormer: Disassembled Transformer with Local Structure Enhancement for 3D Point Cloud Understanding

18 Dec 2023NeurIPS 2023 11arXiv:2312.11112archive 2025-07-28

Lunhao Duan, Shanshan Zhao, Nan Xue, Mingming Gong, Gui-Song Xia, DaCheng Tao

Transformers have been recently explored for 3D point cloud understanding with impressive progress achieved. A large number of points, over 0.1 million, make the global self-attention infeasible for point cloud data. Thus, most methods propose to apply the transformer in a local region, e.g., spherical or cubic window. However, it still contains a large number of Query-Key pairs, which requires high computational costs. In addition, previous methods usually learn the query, key, and value using a linear projection without modeling the local 3D geometric structure. In this paper, we attempt to reduce the costs and model the local geometry prior by developing a new transformer block, named ConDaFormer. Technically, ConDaFormer disassembles the cubic window into three orthogonal 2D planes, leading to fewer points when modeling the attention in a similar range. The disassembling operation is beneficial to enlarging the range of attention without increasing the computational complexity, but ignores some contexts. To provide a remedy, we develop a local structure enhancement strategy that introduces a depth-wise convolution before and after the attention. This scheme can also capture the local geometric information. Taking advantage of these designs, ConDaFormer captures both long-range contextual information and local priors. The effectiveness is demonstrated by experimental results on several 3D point cloud understanding benchmarks. Code is available at https://github.com/LHDuan/ConDaFormer .

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2312.11112")

Code

Syntology Ran 2 of 9 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 2 ran · violated contract.

By repository: official repository: 9 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.

lhduan/condaformer 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

9 samples harvested; 2 ran; 0 honoured the contract we drafted; 7 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

2ran · violated contract
7unverified

Licence: 9 of the 9 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 lhduan/condaformer. “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.

isnan lhduan/condaformer/pcr/utils/losses.py official repository ran · violated contract fingerprinted no licence file found · pointer only · 5f4f4355be28c01e · report
lovasz_grad lhduan/condaformer/pcr/utils/losses.py official repository ran · violated contract fingerprinted no licence file found · pointer only · e85b5d21dc5b8382 · report
batch2offset lhduan/condaformer/pcr/models/utils.py official repository unverified no licence file found · pointer only · 2a2c9e53188de780 · report
grid_sample lhduan/condaformer/pcr/models/condaformer/utils.py official repository unverified no licence file found · pointer only · 66d6bb150bbb2e57 · report
lovasz_softmax lhduan/condaformer/pcr/utils/losses.py official repository unverified no licence file found · pointer only · 82b9b0ff4b3626c9 · report
offset2batch lhduan/condaformer/pcr/models/condaformer/condaformer.py official repository unverified no licence file found · pointer only · 6dd8eac8666461f5 · report
offset2batch lhduan/condaformer/pcr/models/utils.py official repository unverified no licence file found · pointer only · d78aee4794314c59 · report
to_3d_numpy lhduan/condaformer/pcr/models/condaformer/utils.py official repository unverified no licence file found · pointer only · ae72b160c77cb3e4 · report
trunc_normal_ lhduan/condaformer/pcr/models/utils.py official repository unverified no licence file found · pointer only · 5436174f8c0e64e0 · report

Tasks

Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation S3DIS Area5 ConDaFormer mAcc 78.9 #9 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 ConDaFormer mIoU 73.5 #9 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 ConDaFormer oAcc 92.4 #9 of 61 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

Convolution

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