AI Paper Atlas

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

NeurIPS 2026 · Point clouds › Point cloud classification · approach: Point-language and open-vocabulary 3D

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy