paper-with-me

3D Part Segmentation

2개 벤치마크 · 논문 109편 · 이 태스크의 논문 보기 →

Benchmarks

ShapeNet-Part

결과 134개

IntrA

결과 14개

Most implemented

Point Transformer

2020-12-16 · 구현 24개

PCT: Point cloud transformer

2020-12-17 · 구현 11개

Papers

SegviGen: Repurposing 3D Generative Model for Part Segmentation

2026-03-17 · Lin Li, Haoran Feng, Zehuan Huang, Haohua Chen 외 arxiv

We introduce SegviGen, a framework that repurposes native 3D generative models for 3D part segmentation. Existing pipelines either lift strong 2D priors into 3D via distillation or multi-view mask aggregation, often suff…

3D Part Segmentation

PatchAlign3D: Local Feature Alignment for Dense 3D Shape understanding

2026-01-05 · Souhail Hadgi, Bingchen Gong, Ramana Sundararaman, Emery Pierson 외 arxiv

Current foundation models for 3D shapes excel at global tasks (retrieval, classification) but transfer poorly to local part-level reasoning. Recent approaches leverage vision and language foundation models to directly so…

3D Part SegmentationPrompt EngineeringPoint Clouds

Name That Part: 3D Part Segmentation and Naming

2025-12-19 · Soumava Paul, Prakhar Kaushik, Ankit Vaidya, Anand Bhattad 외 arxiv

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. Pr…

3D Part Segmentation

SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation

2025-12-18 · Yueyang Hu, Haiyong Jiang, Haoxuan Song, Jun Xiao 외 arxiv

This work presents a novel framework for few-shot 3D part segmentation. Recent advances have demonstrated the significant potential of 2D foundation models for low-shot 3D part segmentation. However, it is still an open …

3D Part SegmentationGraph Neural Network

sim2art: Accurate Articulated Object Modeling from a Single Video using Synthetic Training Data Only

2025-12-08 · Arslan Artykov, Tom Ravaud, Corentin Sautier, Vincent Lepetit arxiv

Understanding articulated objects from monocular video is a crucial yet challenging task in robotics and digital twin creation. Existing methods often rely on complex multi-view setups, high-fidelity object scans, or fra…

3D Part SegmentationDomain Adaptation

TEXTRIX: Latent Attribute Grid for Native Texture Generation and Beyond

2025-12-02 · Yifei Zeng, Yajie Bao, Jiachen Qian, Shuang Wu 외 arxiv

Prevailing 3D texture generation methods, which often rely on multi-view fusion, are frequently hindered by inter-view inconsistencies and incomplete coverage of complex surfaces, limiting the fidelity and completeness o…

3D Part Segmentation

전체 109편 보기 →