SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals

• URL: http://arxiv.org/abs/2605.18039v1
• Date: Mon, 18 May 2026 08:31:04 GMT
• Title: SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
• Abstract summary: Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology.<n>We propose SGSoft, a unified intrinsic pipeline that constructs a geodesic correspondence field on a canonical template and learns multimodal dense descriptors guided by pretrained semantic priors.<n> SGSoft achieves state-of-the-art inter-category generalization while offering the best accuracy-efficiency trade-off among prior methods.
• Score: 23.94595783675059
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric fidelity, and efficiency. We address this by proposing SGSoft, a unified intrinsic pipeline that (i) constructs a geodesic correspondence field on a canonical template, (ii) learns multimodal dense descriptors guided by pretrained semantic priors with this geodesic correspondence field supervision, (iii) retrieves dense correspondences in a single feed-forward pass via nearest-neighbor search in descriptor space. This formulation enables stable and topology-invariant supervision under large pose variation, structural differences, and remeshing. SGSoft achieves state-of-the-art inter-category generalization while offering the best accuracy-efficiency trade-off among prior methods. It also achieves near real-time inference without pre-alignment, pairwise optimization, or post-refinement. Learned descriptors can be transferred effectively to downstream tasks such as semantic segmentation and deformation transfer, establishing a scalable and deployment-ready paradigm for dense 3D correspondence.

Related papers

• From Extrinsic to Intrinsic: Geodesic-Guided Representation Learning for 3D Geometric Data [56.41479248637621]
  We introduce a novel 3D representation learning paradigm, namely textbfPRISM, for textbfPre-training.<n>PRISM learns embeddings by textbfRecovering the textbfIntrinsic textbfSurface geodesic textbfMetric.<n> Experiments demonstrate that our approach shows satisfactory accuracy, robustness, and high efficiency in geodesic distance prediction.
  arXiv  Detail & Related papers  (2026-06-01T13:54:26Z)
• OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention [80.51557267896938]
  We present OpenGaFF, a novel framework for open-vocabulary 3D scene understanding built upon 3D Gaussian Splatting.<n>At the core of our method is a Gaussian Feature Field that models semantics as a continuous function of Gaussian geometry and appearance.<n>To further enforce object-level semantic consistency, we introduce a structured codebook that serves as a set of shared semantic primitives.
  arXiv  Detail & Related papers  (2026-05-07T12:10:07Z)
• LoST: Level of Semantics Tokenization for 3D Shapes [50.847769883816085]
  State-of-the-art methods rely on geometric level-of-detail (LoD) hierarchies, originally designed for rendering and compression.<n>We propose Level-of-Semantics Tokenization (LoST), which orders salience, such that early prefixes decode complete, plausible shapes.<n>LoST achieves SOTA reconstruction, surpassing previous LoD-based 3D shape tokenizers by large margins on both geometric and semantic reconstruction metrics.
  arXiv  Detail & Related papers  (2026-03-18T17:56:06Z)
• SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization [43.12848612518533]
  We introduce SGMatch, a learning-based framework for semantic-guided non-rigid shape matching.<n> Specifically, we design a Semantic-Guided Local Cross-Attention module that integrates semantic features from vision foundation models into geometric descriptors.<n>We introduce a regularization objective based on conditional flow matching, which supervises a time-varying velocity field to encourage spatial smoothness of the recovered correspondences.
  arXiv  Detail & Related papers  (2026-03-13T12:31:43Z)
• 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)
• Dense Semantic Matching with VGGT Prior [49.42199006453071]
  We propose an approach that retains VGGT's intrinsic strengths by reusing early feature stages, fine-tuning later ones, and adding a semantic head for bidirectional correspondences.<n>Our approach achieves superior geometry awareness, matching reliability, and manifold preservation, outperforming previous baselines.
  arXiv  Detail & Related papers  (2025-09-25T14:56:11Z)
• Hierarchical Neural Semantic Representation for 3D Semantic Correspondence [72.8101601086805]
  We design the hierarchical neural semantic representation (HNSR), which consists of a global semantic feature to capture high-level structure and multi-resolution local geometric features.<n>Second, we design a progressive global-to-local matching strategy, which establishes coarse semantic correspondence using the global semantic feature.<n>Third, our framework is training-free and broadly compatible with various pre-trained 3D generative backbones, demonstrating strong generalization across diverse shape categories.
  arXiv  Detail & Related papers  (2025-09-22T07:23:07Z)
• Matching Shapes Under Different Topologies: A Topology-Adaptive Deformation Guided Approach [6.851721795186258]
  Non-rigid 3D mesh matching is a critical step in computer vision and computer graphics pipelines.<n>We tackle matching meshes that contain topological artefacts which can break the assumption made by current approaches.<n>We are motivated by real-world scenarios such as per-frame multi-view reconstructions, often suffering from topological artefacts.<n>We show that, while not relying on any data-driven prior, our approach applies to highly non-isometric shapes and shapes with topological artefacts, including noisy per-frame multi-view reconstructions, even outperforming methods trained on large datasets in 3D alignment quality.
  arXiv  Detail & Related papers  (2025-09-08T16:29:44Z)
• SIGMA: Scale-Invariant Global Sparse Shape Matching [50.385414715675076]
  We propose a novel mixed-integer programming (MIP) formulation for generating precise sparse correspondences for non-rigid shapes. We show state-of-the-art results for sparse non-rigid matching on several challenging 3D datasets.
  arXiv  Detail & Related papers  (2023-08-16T14:25:30Z)

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.