Name That Part: 3D Part Segmentation and Naming

• URL: http://arxiv.org/abs/2512.18003v1
• Date: Fri, 19 Dec 2025 19:02:36 GMT
• Title: Name That Part: 3D Part Segmentation and Naming
• Abstract summary: We propose ALIGN-Parts, which formulates part naming as a direct set alignment task.<n>Our method decomposes shapes into partlets - implicit 3D part representations - matched to part descriptions via bipartite assignment.<n>Our model supports zero-shot matching to arbitrary descriptions and confidence-calibrated predictions for known categories.
• Score: 13.782629682520422
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We address semantic 3D part segmentation: decomposing objects into parts with meaningful names. While datasets exist with part annotations, their definitions are inconsistent across datasets, limiting robust training. Previous methods produce unlabeled decompositions or retrieve single parts without complete shape annotations. We propose ALIGN-Parts, which formulates part naming as a direct set alignment task. Our method decomposes shapes into partlets - implicit 3D part representations - matched to part descriptions via bipartite assignment. We combine geometric cues from 3D part fields, appearance from multi-view vision features, and semantic knowledge from language-model-generated affordance descriptions. Text-alignment loss ensures partlets share embedding space with text, enabling a theoretically open-vocabulary matching setup, given sufficient data. Our efficient and novel, one-shot, 3D part segmentation and naming method finds applications in several downstream tasks, including serving as a scalable annotation engine. As our model supports zero-shot matching to arbitrary descriptions and confidence-calibrated predictions for known categories, with human verification, we create a unified ontology that aligns PartNet, 3DCoMPaT++, and Find3D, consisting of 1,794 unique 3D parts. We also show examples from our newly created Tex-Parts dataset. We also introduce 2 novel metrics appropriate for the named 3D part segmentation task.

Related papers

• CubePart: An Open-Vocabulary Part-Controllable 3D Generator [25.37244384706095]
  We present CubePart, a generative framework for open-vocabulary, part-controllable 3D mesh generation.<n>Our method generates a set of meshes that assemble into a coherent object while respecting the specified semantic structure.<n>We demonstrate that the resulting assets can be directly integrated into game engines and driven by animation and behavior scripts without manual post-processing.
  arXiv  Detail & Related papers  (2026-05-27T17:22:38Z)
• 3D-DRES: Detailed 3D Referring Expression Segmentation [53.88273255459736]
  We introduce Detailed 3D Referring Expression (3D-DRES), a new task that provides a phrase to 3D instance mapping.<n>We present DetailRefer, a new dataset comprising 54,432 descriptions spanning 11,054 distinct objects.<n>Our experimental results demonstrate that models trained on DetailRefer excel at phrase-level segmentation and show surprising improvements on traditional 3D-RES benchmarks.
  arXiv  Detail & Related papers  (2026-03-03T11:45:54Z)
• PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding [65.55036443711528]
  PartNeXt is a next-generation dataset with over 23,000 high-quality, textured 3D models annotated with fine-grained, hierarchical part labels across 50 categories.<n>We benchmark PartNeXt on two tasks: (1) class-agnostic part segmentation, where state-of-the-art methods struggle with fine-grained and leaf-level parts, and (2) 3D part-centric question answering, a new benchmark for 3D-LLMs that reveals significant gaps in open-vocabulary part grounding.
  arXiv  Detail & Related papers  (2025-10-23T03:06:08Z)
• PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond [70.95930509071451]
  PartField is a feedforward approach for learning part-based 3D features.<n>PartField is up to 20% more accurate and often orders of magnitude faster than other recent class-agnostic part-segmentation methods.
  arXiv  Detail & Related papers  (2025-04-15T17:58:16Z)
• 3D Part Segmentation via Geometric Aggregation of 2D Visual Features [57.20161517451834]
  Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios.<n>Recent works have explored vision-language models (VLMs) as a promising alternative, using multi-view rendering and textual prompting to identify object parts.<n>To address these limitations, we propose COPS, a COmprehensive model for Parts that blends semantics extracted from visual concepts and 3D geometry to effectively identify object parts.
  arXiv  Detail & Related papers  (2024-12-05T15:27:58Z)
• SAMPart3D: Segment Any Part in 3D Objects [23.97392239910013]
  3D part segmentation is a crucial and challenging task in 3D perception, playing a vital role in applications such as robotics, 3D generation, and 3D editing. Recent methods harness the powerful Vision Language Models (VLMs) for 2D-to-3D knowledge distillation, achieving zero-shot 3D part segmentation. In this work, we introduce SAMPart3D, a scalable zero-shot 3D part segmentation framework that segments any 3D object into semantic parts at multiple granularities.
  arXiv  Detail & Related papers  (2024-11-11T17:59:10Z)
• LESS: Label-Efficient and Single-Stage Referring 3D Segmentation [55.06002976797879]
  Referring 3D is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. We propose a novel Referring 3D pipeline, Label-Efficient and Single-Stage, dubbed LESS, which is only under the supervision of efficient binary mask. We achieve state-of-the-art performance on ScanRefer dataset by surpassing the previous methods about 3.7% mIoU using only binary labels.
  arXiv  Detail & Related papers  (2024-10-17T07:47:41Z)
• Search3D: Hierarchical Open-Vocabulary 3D Segmentation [78.47704793095669]
  We introduce Search3D, an approach to construct hierarchical open-vocabulary 3D scene representations.<n>Unlike prior methods, Search3D shifts towards a more flexible open-vocabulary 3D search paradigm.<n>For systematic evaluation, we contribute a scene-scale open-vocabulary 3D part segmentation benchmark based on MultiScan.
  arXiv  Detail & Related papers  (2024-09-27T03:44:07Z)
• PanopticRecon: Leverage Open-vocabulary Instance Segmentation for Zero-shot Panoptic Reconstruction [23.798691661418253]
  We propose a novel zero-shot panoptic reconstruction method from RGB-D images of scenes. We tackle both challenges by propagating partial labels with the aid of dense generalized features. Our method outperforms state-of-the-art methods on the indoor dataset ScanNet V2 and the outdoor dataset KITTI-360.
  arXiv  Detail & Related papers  (2024-07-01T15:06:04Z)

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.