Sparse Compositional Flow Matching by geometric assembly from motion primitives

• URL: http://arxiv.org/abs/2605.23341v1
• Date: Fri, 22 May 2026 07:55:48 GMT
• Title: Sparse Compositional Flow Matching by geometric assembly from motion primitives
• Abstract summary: Embodied trajectories, such as the executable motion sequences of robotic manipulators, underwater vehicles, and mobile robots, are a fundamental output of embodied AI.<n>Modern generative models often treat them as a dense, monolithic signal generated point by point, fitting an intricate high-dimensional posterior while leaving the data's latent structure unmodeled.<n>We argue that a compositional latent structure is a natural choice: many embodied tasks share recurring motion fragments that can be made explicit as a finite repertoire of reusable motion primitives.<n>Existing compositional generators compose in a latent space and rely on post-hoc decoding to relate sampled units to actual trajectory
• Score: 15.40404761023639
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embodied trajectories, such as the executable motion sequences of robotic manipulators, underwater vehicles, and mobile robots, are a fundamental output of embodied AI. Modern generative models often treat them as a dense, monolithic signal generated point by point, fitting an intricate high-dimensional posterior while leaving the data's latent structure unmodeled, the same sample inefficiency long identified by the structured generative model literature. We argue that a compositional latent structure is a natural choice: many embodied tasks share recurring motion fragments that can be made explicit as a finite repertoire of reusable motion primitives, and compositional units naturally align with subtask boundaries to support task decomposition. Existing compositional generators, however, compose in a latent space and rely on post-hoc decoding to relate sampled units to actual trajectory segments. We instead compose directly in the physical trajectory space through a flow-matching framework with two coupled designs. Motion-Primitive Dictionary Learning equips each atom with a learnable length mask and binary starting indicators so the atom itself is the primitive, reused verbatim wherever it is placed. Structural Sparse Flow Matching with Geometric Constraints then generates a binary placement matrix using duration-aware tokenization and a differentiable geometric loss that enforces spatial continuity and temporal contiguity where adjacent primitives meet. On Open X-Embodiment and 3DMoTraj, the framework attains state-of-the-art accuracy and reduces the FDE/ADE ratio from 1.8 to 1.07, improving ADE by 19.2% and FDE by 21.0% over the strongest baseline.

Related papers

• Stable and Scalable Bundle Adjustment of Holistic 3D Structures [99.03818732955783]
  We present a new version of Bundle Adjustment (BA) for 3D computer vision.<n>BA is developed to jointly optimize cameras, poses and 3D points.<n>By group-induced measurements and cross-feature reprojection, we preserve the sparsity of classical point-only 3D regularization.
  arXiv  Detail & Related papers  (2026-09-03T16:08:03Z)
• Learning to Tessellate: Point Cloud Generation via Recursive Spectral Partitioning [58.130498928480456]
  We present PointRSP, an autoregressive framework that reformulates point cloud generation as a topology-preserving tessellation process.<n>PointRSP achieves state-of-the-art performance in generation quality and diversity, demonstrating strong generalization across complex 3D topologies.
  arXiv  Detail & Related papers  (2026-08-03T16:11:43Z)
• MamBOA: State-Space Architecture for Video Recognition [0.0]
  MamBOA is a backbone-agnostic temporal framework that recasts the selective state-space recurrence (S6) as a native motion synthesizer.<n>On Diving48, MamBOA achieves 85.02% Top-1 accuracy with an image-pretrained backbone and 86.24% with a video-pretrained backbone processing the entire video in a single forward pass.
  arXiv  Detail & Related papers  (2026-06-13T12:27:06Z)
• Local Spatiotemporal Convolutional Network for Robust Gait Recognition [7.0676119183443395]
  Gait recognition is a promising biometric technology that identifies individuals through their unique walking patterns.<n>Existing approaches rely on either static appearance features extracted from individual silhouette frames or employ complex sequential models.<n>We propose a Local Stemporal Convolutional Network (LSTCN), a structurally simple yet highly effective dual-branch architecture that endows standard two-dimensional convolutional networks with the capacity to extract temporal information.
  arXiv  Detail & Related papers  (2026-05-14T08:28:49Z)
• Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild [7.4746628878102195]
  Shape-of-You is an unsupervised learning framework for semantic correspondence.<n>It achieves state-of-the-art performance on SPair-71k and AP-10k datasets.
  arXiv  Detail & Related papers  (2026-03-12T07:22:03Z)
• Structural Action Transformer for 3D Dexterous Manipulation [80.07649565189035]
  Cross-embodiment skill transfer is a challenge for high-DoF robotic hands.<n>Existing methods, often relying on 2D observations and temporal-centric action representation, struggle to capture 3D spatial relations.<n>This paper proposes a new 3D dexterous manipulation policy that challenges this paradigm by introducing a structural-centric perspective.
  arXiv  Detail & Related papers  (2026-03-04T11:38:12Z)
• Inverting Self-Organizing Maps: A Unified Activation-Based Framework [39.146761527401424]
  We show that the activation pattern of a SOM can be inverted to recover the exact input under mild geometric conditions.<n>We introduce the Manifold-Aware Unified SOM Inversion and Control (MUSIC) update rule.<n>We validate the approach using synthetic Gaussian mixtures, the MNIST and the Faces in the Wild dataset.
  arXiv  Detail & Related papers  (2026-01-20T11:02:54Z)
• StdGEN++: A Comprehensive System for Semantic-Decomposed 3D Character Generation [57.06461272772509]
  StdGEN++ is a novel and comprehensive system for generating high-fidelity, semantically decomposed 3D characters from diverse inputs.<n>It achieves state-of-the-art performance, significantly outperforming existing methods in geometric accuracy and semantic disentanglement.<n>The resulting structural independence unlocks advanced downstream capabilities, including non-destructive editing, physics-compliant animation, and gaze tracking.
  arXiv  Detail & Related papers  (2026-01-12T15:41:27Z)
• IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes [25.939318593012484]
  Reconstructing dynamic driving scenes is essential for developing autonomous systems through sensor-realistic simulation.<n>We present IDSplat, a self-supervised 3D Gaussian Splatting framework that reconstructs dynamic scenes with explicit instance decomposition and learnable motion trajectories.<n>Our method achieves competitive reconstruction quality while maintaining instance-level decomposition and generalizes across diverse sequences and view densities without retraining.
  arXiv  Detail & Related papers  (2025-11-24T15:48:08Z)
• SegSplat: Feed-forward Gaussian Splatting and Open-Set Semantic Segmentation [114.57192386025373]
  SegSplat is a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding.<n>This work represents a significant step towards practical, on-the-fly generation of semantically aware 3D environments.
  arXiv  Detail & Related papers  (2025-11-23T10:26:38Z)
• SVRecon: Sparse Voxel Rasterization for Surface Reconstruction [60.92372415355283]
  We extend the recently proposed sparse voxelization paradigm to the task of high-fidelity surface reconstruction by integrating SVRecon.<n>Our method achieves strong reconstruction accuracy while having consistently speedy convergence.
  arXiv  Detail & Related papers  (2025-11-21T16:32:01Z)
• Bidirectional Feature-aligned Motion Transformation for Efficient Dynamic Point Cloud Compression [97.66080040613726]
  We propose a Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space.<n>Bi-FMT aligns features across both past and future frames to produce temporally consistent latent representations.<n>We show Bi-FMT surpasses D-DPCC and AdaDPCC in both compression efficiency and runtime.
  arXiv  Detail & Related papers  (2025-09-18T03:51:06Z)
• ReCoM: Realistic Co-Speech Motion Generation with Recurrent Embedded Transformer [58.49950218437718]
  We present ReCoM, an efficient framework for generating high-fidelity and generalizable human body motions synchronized with speech.<n>The core innovation lies in the Recurrent Embedded Transformer (RET), which integrates Dynamic Embedding Regularization (DER) into a Vision Transformer (ViT) core architecture.<n>To enhance model robustness, we incorporate the proposed DER strategy, which equips the model with dual capabilities of noise resistance and cross-domain generalization.
  arXiv  Detail & Related papers  (2025-03-27T16:39:40Z)

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.