RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings

• URL: http://arxiv.org/abs/2605.10706v1
• Date: Mon, 11 May 2026 15:20:01 GMT
• Title: RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings
• Abstract summary: We present a new class of efficient attention mechanisms applying universal 3D Relative Positional computation (RPE) methods given by arbitrary integrable modulation functions $f$.<n>They lead to the new class of 3D-Transformer models, called textitRelFlexformers, flexibly integrating those RPEs.<n>Our empirical evaluation on a large portfolio of 3D datasets confirms quality improvements provided by the NU-FFT-driven attention modulation techniques in the RelFlexformers.
• Score: 35.47034796583214
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a new class of efficient attention mechanisms applying universal 3D Relative Positional Encoding (RPE) methods given by arbitrary integrable modulation functions $f$. They lead to the new class of 3D-Transformer models, called \textit{RelFlexformers}, flexibly integrating those RPEs, and characterized by the $O(L \log L)$ time complexity of the attention computation for the $L$-length input sequences. RelFlexformers builds on the theory of the Non-Uniform Fourier Transform (NU-FFT), naturally generalizing several existing efficient RPE-attention methods from structured settings with tokens homogeneously embedded in unweighted grids into general non-structured heterogeneous scenarios, where tokens' positions are arbitrarily distributed in the corresponding 3D spaces. As such, RelFlexformers can be applied in particular to model point clouds. Our extensive empirical evaluation on a large portfolio of 3D datasets confirms quality improvements provided by the NU-FFT-driven attention modulation techniques in the RelFlexformers.

Related papers

• 3D Fourier-based Global Feature Extraction for Hyperspectral Image Classification [4.139698879651128]
  We propose Hybrid GFNet, a novel architecture that integrates localized 3D convolutional feature extraction with frequency-domain global filtering.<n>The 3D convolutional layers capture fine-grained local spatial-spectral structures, while the Fourier-based global filtering modules efficiently model long-range dependencies and suppress noise.<n>To further mitigate the severe class imbalance commonly observed in HSIC, HGFNet incorporates an Adaptive Focal Loss (AFL) that dynamically adjusts class-wise focusing and weighting.
  arXiv  Detail & Related papers  (2026-03-17T12:02:28Z)
• FUSER: Feed-Forward MUltiview 3D Registration Transformer and SE(3)$^N$ Diffusion Refinement [39.19949818461193]
  F is the first feed-forward multiview registration transformer that processes all scans in a unified, compact latent space.<n>F predicts global poses without any pairwise estimation.<n>Experiments on 3DMatch, ScanNet and ArkitScenes demonstrate that our approach achieves the superior registration accuracy and outstanding computational efficiency.
  arXiv  Detail & Related papers  (2025-12-10T07:11:22Z)
• Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazing [26.57698394898644]
  We propose a novel dehazing framework based on a Multi-State Perception paradigm.<n>Fourier-RWKV delivers state-of-the-art performance across diverse haze scenarios.
  arXiv  Detail & Related papers  (2025-12-09T01:35:56Z)
• Learning Modulated Transformation in GANs [69.95217723100413]
  We equip the generator in generative adversarial networks (GANs) with a plug-and-play module, termed as modulated transformation module (MTM) MTM predicts spatial offsets under the control of latent codes, based on which the convolution operation can be applied at variable locations. It is noteworthy that towards human generation on the challenging TaiChi dataset, we improve the FID of StyleGAN3 from 21.36 to 13.60, demonstrating the efficacy of learning modulated geometry transformation.
  arXiv  Detail & Related papers  (2023-08-29T17:51:22Z)
• Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers [71.32827362323205]
  We propose a new class of linear Transformers calledLearner-Transformers (Learners) They incorporate a wide range of relative positional encoding mechanisms (RPEs) These include regular RPE techniques applied for sequential data, as well as novel RPEs operating on geometric data embedded in higher-dimensional Euclidean spaces.
  arXiv  Detail & Related papers  (2023-02-03T18:57:17Z)
• DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets [95.84755169585492]
  We present Dynamic Sparse Voxel Transformer (DSVT), a single-stride window-based voxel Transformer backbone for outdoor 3D perception. Our model achieves state-of-the-art performance with a broad range of 3D perception tasks.
  arXiv  Detail & Related papers  (2023-01-15T09:31:58Z)
• Holographic-(V)AE: an end-to-end SO(3)-Equivariant (Variational) Autoencoder in Fourier Space [0.0]
  Group-equivariant neural networks have emerged as a data-efficient approach to solve classification and regression tasks. Here, we present Holographic-(Variational) Autoencoder in Fourier space, suitable for unsupervised learning and generation of data distributed around a specified origin in 3D. We show that the learned latent space efficiently encodes the categorical features of spherical images.
  arXiv  Detail & Related papers  (2022-09-30T16:25:20Z)
• 3D Equivariant Graph Implicit Functions [51.5559264447605]
  We introduce a novel family of graph implicit functions with equivariant layers that facilitates modeling fine local details. Our method improves over the existing rotation-equivariant implicit function from 0.69 to 0.89 on the ShapeNet reconstruction task.
  arXiv  Detail & Related papers  (2022-03-31T16:51:25Z)
• FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization [73.41395947275473]
  We propose a novel frequency-aware architecture, in which the domain-specific features are filtered out in the transformed frequency domain. Experiments on three benchmarks demonstrate significant performance, outperforming the state-of-the-art methods by a margin of 3%, 4% and 9%, respectively.
  arXiv  Detail & Related papers  (2022-03-24T07:26:29Z)
• Dense Non-Rigid Structure from Motion: A Manifold Viewpoint [162.88686222340962]
  Non-Rigid Structure-from-Motion (NRSfM) problem aims to recover 3D geometry of a deforming object from its 2D feature correspondences across multiple frames. We show that our approach significantly improves accuracy, scalability, and robustness against noise.
  arXiv  Detail & Related papers  (2020-06-15T09:15:54Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.