Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation

• URL: http://arxiv.org/abs/2609.06218v1
• Date: Sat, 05 Sep 2026 18:28:35 GMT
• Title: Branch-Centric Tokenization and Test-Time Augmentation for Skeleton Generation
• Abstract summary: We introduce branch-centric tokenization, a branch-aware representation that encodes connectivity directly in the sequence.<n>We also introduce view-augmented generation, a test-time augmentation procedure that applies axis-aligned rotations to the input mesh.<n> Experiments show that our method achieves better skeleton prediction accuracy than state-of-the-art methods.
• Score: 4.947134980425439
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic skeleton generation involves predicting both joint positions and skeletal connectivity. However, existing approaches struggle to encode branch structures into token sequences and do not use test-time computation effectively. We study these choices within a unified autoregressive framework. First, we introduce branch-centric tokenization, a branch-aware representation that places structurally related elements next to each other and encodes connectivity directly in the sequence. Compared with standard BFS-style serialization, this representation yields more compact sequences. Second, we introduce view-augmented generation, a test-time augmentation procedure that applies axis-aligned rotations to the input mesh, maps all predictions back to a common frame, and selects the final skeleton based on mesh coverage and consistency among predictions from different views. Experiments show that our method achieves better skeleton prediction accuracy than state-of-the-art methods. In particular, our method reduces the CD-J2B error by 16.9% on the Articulation-XL2.0 dataset compared to the strongest directly comparable baseline, Auto-Connect. Qualitative results on in-the-wild meshes further demonstrate generalization across diverse inputs.

Related papers

• SuperGrasp: Single-View Object Grasping via Superquadric Similarity Matching, Evaluation, and Refinement [27.71481975135778]
  SuperGrasp is a novel two-stage framework for single-view grasping with parallel-jaw grippers.<n>In the first stage, we introduce a Similarity Matching Module that efficiently retrieves grasp candidates.<n>In the second stage, we propose E-RNet, an end-to-end network that expands the graspaware region.
  arXiv  Detail & Related papers  (2026-03-31T04:25:53Z)
• Bridging the Divide: End-to-End Sequence-Graph Learning [47.95529678412846]
  We argue that sequences and graphs are not separate problems but complementary facets of the same dataset.<n>We introduce BRIDGE, a unified end-to-end architecture that couples a sequence encoder with a GNN under a single objective.<n>We show that BRIDGE consistently outperforms static GNNs, temporal graph methods, and sequence-only baselines on ranking and classification metrics.
  arXiv  Detail & Related papers  (2025-10-29T03:06:54Z)
• Learning Discrete Bayesian Networks with Hierarchical Dirichlet Shrinkage [52.914168158222765]
  We detail a comprehensive Bayesian framework for learning DBNs.<n>We give a novel Markov chain Monte Carlo (MCMC) algorithm utilizing parallel Langevin proposals to generate exact posterior samples.<n>We apply our methodology to uncover prognostic network structure from primary breast cancer samples.
  arXiv  Detail & Related papers  (2025-09-16T17:24:35Z)
• Improving action segmentation via explicit similarity measurement [5.303583360581161]
  We propose an explicit similarity evaluation across frames and predictions to enhance the segmentation accuracy.<n>Our supervised learning architecture uses frame-level multi-resolution features as input to Transformer encoders.<n>We apply a newly proposed boundary correction algorithm that operates based on feature similarity between consecutive frames.<n>We also propose a fully unsupervised boundary detection-correction that identifies segment boundaries based solely on feature similarity without any training.
  arXiv  Detail & Related papers  (2025-02-15T08:02:38Z)
• Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence [56.092059713922744]
  We show that using high-level contextualized features as prediction targets can achieve superior performance. Specifically, we propose Skeleton2vec, a simple and efficient self-supervised 3D action representation learning framework. Our proposed Skeleton2vec outperforms previous methods and achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2024-01-01T12:08:35Z)
• Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionality [84.94877848357896]
  Recent datasets expose the lack of the systematic generalization ability in standard sequence-to-sequence models. We analyze this behavior of seq2seq models and identify two contributing factors: a lack of mutual exclusivity bias and the tendency to memorize whole examples. We show substantial empirical improvements using standard sequence-to-sequence models on two widely-used compositionality datasets.
  arXiv  Detail & Related papers  (2022-11-28T17:36:41Z)
• Correspondence Matters for Video Referring Expression Comprehension [64.60046797561455]
  Video Referring Expression (REC) aims to localize the referent objects described in the sentence to visual regions in the video frames. Existing methods suffer from two problems: 1) inconsistent localization results across video frames; 2) confusion between the referent and contextual objects. We propose a novel Dual Correspondence Network (dubbed as DCNet) which explicitly enhances the dense associations in both the inter-frame and cross-modal manners.
  arXiv  Detail & Related papers  (2022-07-21T10:31:39Z)
• Parameter Decoupling Strategy for Semi-supervised 3D Left Atrium Segmentation [0.0]
  We present a novel semi-supervised segmentation model based on parameter decoupling strategy to encourage consistent predictions from diverse views. Our method has achieved a competitive result over the state-of-the-art semisupervised methods on the Atrial Challenge dataset.
  arXiv  Detail & Related papers  (2021-09-20T14:51:42Z)
• Complex Event Forecasting with Prediction Suffix Trees: Extended Technical Report [70.7321040534471]
  Complex Event Recognition (CER) systems have become popular in the past two decades due to their ability to "instantly" detect patterns on real-time streams of events. There is a lack of methods for forecasting when a pattern might occur before such an occurrence is actually detected by a CER engine. We present a formal framework that attempts to address the issue of Complex Event Forecasting.
  arXiv  Detail & Related papers  (2021-09-01T09:52:31Z)

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.