Research map / 3D vision / Human pose estimation
Coarse-to-Fine 3D Part Assembly via Semantic Super-Parts and Symmetry-Aware Pose Estimation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes CFPA, a two-stage coarse-to-fine framework for 3D part assembly that uses semantic abstraction (super-parts) and symmetry-aware pose estimation.
Problem
3D shape assembly from basic parts requires both precise local geometric reasoning for accurate component placement and global structural understanding for semantic coherence and plausible configurations.
Approach
A two-stage pipeline that first groups basic parts into semantic super-parts (coarse, global structure) and then estimates fine-grained poses with symmetry-aware reasoning (local geometry).
Closest papers by meaning
- Imagine: Image-Guided 3D Part Assembly with Structure Knowledge Graph (AAAI 2025 · similarity 0.92)
- Generative 3D Part Assembly via Part-Whole-Hierarchy Message Passing (CVPR 2024 · similarity 0.92)
- Category-Level Multi-Part Multi-Joint 3D Shape Assembly (CVPR 2024 · similarity 0.88)
- Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation (CVPR 2025 · similarity 0.88)
- 3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition (NeurIPS 2024 · similarity 0.87)
- Neural Assembler: Learning to Generate Fine-Grained Robotic Assembly Instructions from Multi-View Images (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.