Papers › MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions

MinkUNeXt: Point Cloud-based Large-scale Place Recognition using 3D Sparse Convolutions

12 Mar 2024arXiv:2403.07593archive 2025-07-28

J. J. Cabrera, A. Santo, A. Gil, C. Viegas, L. Payá

This paper presents MinkUNeXt, an effective and efficient architecture for place-recognition from point clouds entirely based on the new 3D MinkNeXt Block, a residual block composed of 3D sparse convolutions that follows the philosophy established by recent Transformers but purely using simple 3D convolutions. Feature extraction is performed at different scales by a U-Net encoder-decoder network and the feature aggregation of those features into a single descriptor is carried out by a Generalized Mean Pooling (GeM). The proposed architecture demonstrates that it is possible to surpass the current state-of-the-art by only relying on conventional 3D sparse convolutions without making use of more complex and sophisticated proposals such as Transformers, Attention-Layers or Deformable Convolutions. A thorough assessment of the proposal has been carried out using the Oxford RobotCar and the In-house datasets. As a result, MinkUNeXt proves to outperform other methods in the state-of-the-art.

PaperPDFCode

Code

juanjo-cabrera/minkunext 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DecoderPhilosophy

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationConcatenated Skip ConnectionConvolutionGeneralized Mean PoolingMax PoolingReLUResidual BlockResidual ConnectionSparse ConvolutionsU-Net

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