Papers › Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection

15 Jun 2024arXiv:2406.10700archive 2025-07-28

Guowen Zhang, Lue Fan, Chenhang He, Zhen Lei, Zhaoxiang Zhang, Lei Zhang

Serialization-based methods, which serialize the 3D voxels and group them into multiple sequences before inputting to Transformers, have demonstrated their effectiveness in 3D object detection. However, serializing 3D voxels into 1D sequences will inevitably sacrifice the voxel spatial proximity. Such an issue is hard to be addressed by enlarging the group size with existing serialization-based methods due to the quadratic complexity of Transformers with feature sizes. Inspired by the recent advances of state space models (SSMs), we present a Voxel SSM, termed as Voxel Mamba, which employs a group-free strategy to serialize the whole space of voxels into a single sequence. The linear complexity of SSMs encourages our group-free design, alleviating the loss of spatial proximity of voxels. To further enhance the spatial proximity, we propose a Dual-scale SSM Block to establish a hierarchical structure, enabling a larger receptive field in the 1D serialization curve, as well as more complete local regions in 3D space. Moreover, we implicitly apply window partition under the group-free framework by positional encoding, which further enhances spatial proximity by encoding voxel positional information. Our experiments on Waymo Open Dataset and nuScenes dataset show that Voxel Mamba not only achieves higher accuracy than state-of-the-art methods, but also demonstrates significant advantages in computational efficiency.

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="2406.10700")

Code

Syntology Ran 3 of 10 code samples harvested from 1 repository linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 10 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

gwenzhang/voxel-mamba officialmentioned in papermentioned on GitHubpytorchApache-2.0 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

10 samples harvested; 3 ran; 0 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.

1ran · our draft was wrong
2ran
7unverified

Licence: 0 of the 10 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 gwenzhang/voxel-mamba. “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.

get_hilbert_index_2d_mamba_lite gwenzhang/voxel-mamba/pcdet/models/model_utils/voxel_mamba_utils.py official repository ran Apache-2.0 (permissive) · 992f09f880c252a5 · report
get_hilbert_index_3d_mamba_lite gwenzhang/voxel-mamba/pcdet/models/model_utils/voxel_mamba_utils.py official repository ran Apache-2.0 (permissive) · b54b5bd51a6e1d22 · report
selective_scan_ref gwenzhang/voxel-mamba/mamba/mamba_ssm/ops/selective_scan_interface.py official repository ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ba7b868fec181b57 · report
decode gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/generation.py official repository unverified Apache-2.0 (permissive) · eda7b73324d5e67e · report
layer_norm_ref gwenzhang/voxel-mamba/mamba/mamba_ssm/ops/triton/layernorm.py official repository unverified Apache-2.0 (permissive) · 2ce8fcf5bedd19ec · report
load_config_hf gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/hf.py official repository unverified Apache-2.0 (permissive) · 7a8ab4bf37f8fa41 · report
load_state_dict_hf gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/hf.py official repository unverified Apache-2.0 (permissive) · 70607b36f7d19351 · report
modify_logit_for_repetition_penalty gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/generation.py official repository unverified Apache-2.0 (permissive) · da95e9a7906f3d52 · report
rms_norm_ref gwenzhang/voxel-mamba/mamba/mamba_ssm/ops/triton/layernorm.py official repository unverified Apache-2.0 (permissive) · ab802ae3195c6316 · report
sample gwenzhang/voxel-mamba/mamba/mamba_ssm/utils/generation.py official repository unverified Apache-2.0 (permissive) · 8eafd3cf90152c82 · report

Tasks

3D Object DetectionComputational EfficiencyMambaObject DetectionState Space Modelsobject-detection

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