# Clio: Real-time Task-Driven Open-Set 3D Scene Graphs

arXiv: https://arxiv.org/abs/2404.13696 · HTML: https://mlsanity.com/paper/2404.13696/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2024.

## Built on by (most cited first, 30 of 81)

- [VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold](https://mlsanity.com/paper/2505.12549/) (2025)
- [GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering](https://mlsanity.com/paper/2412.14480/) (2024)
- [DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation](https://mlsanity.com/paper/2411.04999/) (2024)
- [Search3D: Hierarchical Open-Vocabulary 3D Segmentation](https://mlsanity.com/paper/2409.18431/) (2024)
- [What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models](https://mlsanity.com/paper/2512.03422/) (2025)
- [VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction](https://mlsanity.com/paper/2601.19887/) (2026)
- [FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction](https://mlsanity.com/paper/2503.07909/) (2025)
- [RayFronts: Open-Set Semantic Ray Frontiers for Online Scene Understanding and Exploration](https://mlsanity.com/paper/2504.06994/) (2025)
- [Describe Anything Anywhere At Any Moment](https://mlsanity.com/paper/2512.00565/) (2025)
- [SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments](https://mlsanity.com/paper/2410.03035/) (2024)
- [RelationField: Relate Anything in Radiance Fields](https://mlsanity.com/paper/2412.13652/) (2024)
- [The Bare Necessities: Designing Simple, Effective Open-Vocabulary Scene Graphs](https://mlsanity.com/paper/2412.01539/) (2024)
- [Air-Ground Collaboration for Language-Specified Missions in Unknown Environments](https://mlsanity.com/paper/2505.09108/) (2025)
- [Articulated 3D Scene Graphs for Open-World Mobile Manipulation](https://mlsanity.com/paper/2602.16356/) (2026)
- [KeySG: Hierarchical Keyframe-Based 3D Scene Graphs](https://mlsanity.com/paper/2510.01049/) (2025)
- [MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning](https://mlsanity.com/paper/2505.03035/) (2025)
- [MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Model for Embodied Task Planning](https://mlsanity.com/paper/2512.16909/) (2025)
- [ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis](https://mlsanity.com/paper/2504.06553/) (2025)
- [FindAnything: Open-Vocabulary and Object-Centric Mapping for Robot Exploration in Any Environment](https://mlsanity.com/paper/2504.08603/) (2025)
- [CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity](https://mlsanity.com/paper/2506.16652/) (2025)
- [OpenSU3D: Open World 3D Scene Understanding using Foundation Models](https://mlsanity.com/paper/2407.14279/) (2024)
- [WildLMa: Long Horizon Loco-Manipulation in the Wild](https://mlsanity.com/paper/2411.15131/) (2024)
- [DualMap: Online Open-Vocabulary Semantic Mapping for Natural Language Navigation in Dynamic Changing Scenes](https://mlsanity.com/paper/2506.01950/) (2025)
- [Language-Grounded Hierarchical Planning and Execution with Multi-Robot 3D Scene Graphs](https://mlsanity.com/paper/2506.07454/) (2025)
- [GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting](https://mlsanity.com/paper/2508.14278/) (2025)
- [Bayesian Fields: Task-driven Open-Set Semantic Gaussian Splatting](https://mlsanity.com/paper/2503.05949/) (2025)
- [Social 3D Scene Graphs: Modeling Human Actions and Relations for Interactive Service Robots](https://mlsanity.com/paper/2509.24966/) (2025)
- [RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.10168/) (2026)
- [FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning](https://mlsanity.com/paper/2604.03696/) (2026)
- [CuriousBot: Interactive Mobile Exploration via Actionable 3D Relational Object Graph](https://mlsanity.com/paper/2501.13338/) (2025)

## Abstract (arXiv)

Modern tools for class-agnostic image segmentation (e.g., SegmentAnything) and open-set semantic understanding (e.g., CLIP) provide unprecedented opportunities for robot perception and mapping. While traditional closed-set metric-semantic maps were restricted to tens or hundreds of semantic classes, we can now build maps with a plethora of objects and countless semantic variations. This leaves us with a fundamental question: what is the right granularity for the objects (and, more generally, for the semantic concepts) the robot has to include in its map representation? While related work implicitly chooses a level of granularity by tuning thresholds for object detection, we argue that such a choice is intrinsically task-dependent. The first contribution of this paper is to propose a task-driven 3D scene understanding problem, where the robot is given a list of tasks in natural language and has to select the granularity and the subset of objects and scene structure to retain in its map that is sufficient to complete the tasks. We show that this problem can be naturally formulated using the Information Bottleneck (IB), an established information-theoretic framework. The second contribution is an algorithm for task-driven 3D scene understanding based on an Agglomerative IB approach, that is able to cluster 3D primitives in the environment into task-relevant objects and regions and executes incrementally. The third contribution is to integrate our task-driven clustering algorithm into a real-time pipeline, named Clio, that constructs a hierarchical 3D scene graph of the environment online using only onboard compute, as the robot explores it. Our final contribution is an extensive experimental campaign showing that Clio not only allows real-time construction of compact open-set 3D scene graphs, but also improves the accuracy of task execution by limiting the map to relevant semantic concepts.