← Back to all news
arXiv Computer Vision By Yiqun Zhao, Jiachen Xu, Yihao Zhi, Yunfei Zhao, Zibo Zhao, Xintong Han, Chunchao Guo, Shenghua Gao

FlexPart: Text-Controlled Semantics-Aware 3D Part Segmentation at Flexible Granularity

Read the original on arXiv Computer Vision →

FlexPart is a new framework that enables text‑controlled, semantics‑aware 3D mesh segmentation at any desired granularity. It introduces a holistic control prompt that combines part names with location and shape clauses, and uses a Vision‑Language Model pipeline to generate a large multi‑granularity dataset. The model produces a view‑independent part‑identity field in 3D space, and an inference‑time VLM planner can auto‑complete descriptive clauses from 2D renderings, allowing users to specify parts with ordinary words. FlexPart outperforms strong baselines by up to 22% in mIoU on its benchmark and improves selective segmentation by 35% over click‑driven methods.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 14

UniPart: Towards Zero-shot Language-Grounded 3D Part Segmentation for Embodied Interaction

arXiv:2609.12898v1 Announce Type: new Abstract: Fine-grained robotic manipulation depends on understanding parts, not only whole objects. Existing 3D foundation models tend to be either generalized b...

By Xinqiang Yu, Zekun qi, Jiawei He, Wenyao Zhang, Xuchuan Chen, Guaocai Yao, Li Yi, Zhaoxiang Zhang, He Wang
llmsragcomputer-visionroboticsfine-tuningmultimodalbenchmarks
More like this →
arXiv Computer Vision
2d ago

A Unified Framework for Image-to-3D Part Generation via Variable Granularity

FlexPart is a unified image‑to‑3D part generation framework that allows variable‑granularity geometric conditions—ranging from sparse points to dense bounding boxes and masks—within a single model. It uses gated adaptive modulation to integrate heterogeneous inputs and an asymmetric geometric guidance mechanism to align representations across granularities, improving geometric consistency and inter‑task synergy. On the PartVerseXL dataset, FlexPart achieves a 16.6% reduction in Part CD compared to TripoSG + SAM3D and a 10.5% reduction compared to OmniPart while maintaining competitive whole‑mesh quality.

By Qiwen Gu, Xin Zhou, Xiwu Chen, Zhongyang Zhu, Zhuo Zhang, Junqiao Zhao
multimodal
More like this →