TORA: Topological Representation Alignment for 3D Shape Assembly

• URL: http://arxiv.org/abs/2604.04050v1
• Date: Sun, 05 Apr 2026 10:47:52 GMT
• Title: TORA: Topological Representation Alignment for 3D Shape Assembly
• Abstract summary: Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which cross-part interactions should drive the motion.<n>We introduce TORA, a topology-first representation alignment framework that distills relational structure from a frozen pretrained 3D encoder into the flow-matching backbone during training.<n>Experiments on five benchmarks spanning geometric, semantic, and inter-object assembly demonstrate state-of-the-art performance, with particularly pronounced gains in zero-shot transfer to unseen real-world and synthetic datasets.
• Score: 48.12655111974345
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which cross-part interactions should drive the motion. We introduce TORA, a topology-first representation alignment framework that distills relational structure from a frozen pretrained 3D encoder into the flow-matching backbone during training. We first realize this via simple instantiation, token-wise cosine matching, which injects the learned geometric descriptors from the teacher representation. We then extend to employ a Centered Kernel Alignment (CKA) loss to match the similarity structure between student and teacher representations for enhanced topological alignment. Through systematic probing of diverse 3D encoders, we show that geometry- and contact-centric teacher properties, not semantic classification ability, govern alignment effectiveness, and that alignment is most beneficial at later transformer layers where spatial structure naturally emerges. TORA introduces zero inference overhead while yielding two consistent benefits: faster convergence (up to 6.9$\times$) and improved accuracy in-distribution, along with greater robustness under domain shift. Experiments on five benchmarks spanning geometric, semantic, and inter-object assembly demonstrate state-of-the-art performance, with particularly pronounced gains in zero-shot transfer to unseen real-world and synthetic datasets. Project page: https://nahyuklee.github.io/tora.

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)
• A Persistent Homology Design Space for 3D Point Cloud Deep Learning [5.810033007426438]
  Persistent Homology (PH) offers stable, multi-scale descriptors of intrinsic shape structure.<n>Despite strong theoretical guarantees and increasing empirical adoption, its integration into deep learning for point clouds remains largely ad hoc and architecturally peripheral.<n>In this work, we introduce a unified design space for Persistent-Homology driven learning in 3D point clouds.
  arXiv  Detail & Related papers  (2026-04-05T22:38:37Z)
• FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation [15.271467111162714]
  FAST3DIS is an end-to-end approach that effectively bypasses post-hoc clustering.<n>We introduce a 3D-anchored, query-based Transformer architecture built upon a foundational depth backbone.<n> Experiments on complex indoor 3D datasets demonstrate that our approach achieves competitive segmentation accuracy.
  arXiv  Detail & Related papers  (2026-03-27T00:45:31Z)
• ProFuse: Efficient Cross-View Context Fusion for Open-Vocabulary 3D Gaussian Splatting [1.1470070927586018]
  ProFuse is an efficient context-aware framework for open-vocabulary 3D scene understanding with 3D Gaussian Splatting (3DGS)<n>The pipeline enhances cross-view consistency and intra-mask cohesion within a direct registration setup.<n>ProFuse achieves strong open-vocabulary 3DGS understanding while completing semantic attachment in about five minutes per scene.
  arXiv  Detail & Related papers  (2026-01-08T09:20:46Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• Rep3D: Re-parameterize Large 3D Kernels with Low-Rank Receptive Modeling for Medical Imaging [15.142146104837005]
  Rep3D is a 3D convolutional framework that incorporates a learnable spatial volumetric prior into large kernel training.<n>Rep3D offers an interpretable, and scalable solution for 3D medical image analysis.
  arXiv  Detail & Related papers  (2025-05-26T07:12:56Z)
• 3D-PointZshotS: Geometry-Aware 3D Point Cloud Zero-Shot Semantic Segmentation Narrowing the Visual-Semantic Gap [10.744510913722817]
  3D-PointZshotS is a geometry-aware zero-shot segmentation framework.<n>We integrate LGPs into a generator via a cross-attention mechanism, enriching semantic features with fine-grained geometric details.<n>We re-present visual and semantic features in a shared space, bridging the semantic-visual gap and facilitating knowledge transfer to unseen classes.
  arXiv  Detail & Related papers  (2025-04-16T19:17:12Z)
• 3D Geometric Shape Assembly via Efficient Point Cloud Matching [59.241448711254485]
  We introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad.
  arXiv  Detail & Related papers  (2024-07-15T08:50:02Z)
• Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis [66.49788145564004]
  We present an unsupervised deep neural architecture called Flattening-Net to represent irregular 3D point clouds of arbitrary geometry and topology. Our methods perform favorably against the current state-of-the-art competitors.
  arXiv  Detail & Related papers  (2022-12-17T15:05:25Z)
• Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes [86.2129580231191]
  Adjoint Rigid Transform (ART) Network is a neural module which can be integrated with a variety of 3D networks. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks. We will release our code and pre-trained models for further research.
  arXiv  Detail & Related papers  (2021-02-01T20:58:45Z)
• 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.