Research map / Point clouds / Point cloud classification
GraphWrit3R: End-to-End Writing of Scene Graphs for Multi-Modal 3D Scenes
Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar, Sebastian Koch, Iro Armeni, Luc V Gool, Danda Pani Paudel
Read the paperCheck your idea against 137,217 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 GraphWrit3R, an end-to-end approach for generating 3D scene graphs from multi-modal 3D scene inputs, avoiding complex multi-stage pipelines with explicit intermediate representations.
Problem
Current 3D scene graph generation relies on complex multi-stage pipelines with explicit intermediate representations, making systems fragile and prone to error propagation.
Approach
Generates scene graphs end-to-end directly from multi-modal 3D scene data, removing explicit intermediate representations and the multi-stage pipeline structure.
Closest papers by meaning
- DepWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors (ECCV 2026 · similarity 0.92)
- GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs (CVPR 2024 · similarity 0.91)
- Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships (CVPR 2024 · similarity 0.90)
- MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations (NeurIPS 2024 · similarity 0.90)
- Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction (NeurIPS 2025 · similarity 0.90)
- Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces (CVPR 2025 · similarity 0.89)
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.
