Cover Image

Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bharadwaj, Sagar, Ma, Ziyong, Ghosh, Anurag, Seshan, Srinivasan, Rowe, Anthony
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

OpenFLAME: Federated Visual Positioning System to Enable Large-Scale Augmented Reality Applications
by: Bharadwaj, Sagar, et al.
Published: (2025)

ZING-3D: Zero-shot Incremental 3D Scene Graphs via Vision-Language Models
by: Saxena, Pranav, et al.
Published: (2025)

SAGE: Scalable Agentic 3D Scene Generation for Embodied AI
by: Xia, Hongchi, et al.
Published: (2026)

SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
by: Yin, Hang, et al.
Published: (2024)

3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
by: Yang, Yuncong, et al.
Published: (2024)

HIPPo: Harnessing Image-to-3D Priors for Model-free Zero-shot 6D Pose Estimation
by: Liu, Yibo, et al.
Published: (2025)

LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency
by: Yan, Weilong, et al.
Published: (2026)

SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
by: Huang, Jiaxin, et al.
Published: (2025)

Language-Assisted 3D Scene Understanding
by: Wu, Yanmin, et al.
Published: (2023)

Multi-modal Situated Reasoning in 3D Scenes
by: Linghu, Xiongkun, et al.
Published: (2024)

Gradient-Driven 3D Segmentation and Affordance Transfer in Gaussian Splatting Using 2D Masks
by: Joseph, Joji, et al.
Published: (2024)

Articulate3D: Holistic Understanding of 3D Scenes as Universal Scene Description
by: Halacheva, Anna-Maria, et al.
Published: (2024)

SceneGraphGrounder: Zero-Shot 3D Visual Grounding via Structured Scene Graph Matching
by: Sun, Xuefei, et al.
Published: (2026)

GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond
by: Halacheva, Anna-Maria, et al.
Published: (2025)

Zero-shot Reconstruction of In-Scene Object Manipulation from Video
by: Lin, Dixuan, et al.
Published: (2025)

PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding
by: Wen, Junjie, et al.
Published: (2026)

Zero-Shot 3D Visual Grounding from Vision-Language Models
by: Li, Rong, et al.
Published: (2025)

ViTa-Zero: Zero-shot Visuotactile Object 6D Pose Estimation
by: Li, Hongyu, et al.
Published: (2025)

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning
by: Hao, Jinkun, et al.
Published: (2025)

SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models
by: Zantout, Nader, et al.
Published: (2025)

VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model
by: Wu, Pengying, et al.
Published: (2024)

SHOW3D: Capturing Scenes of 3D Hands and Objects in the Wild
by: Rim, Patrick, et al.
Published: (2026)

REACT3D: Recovering Articulations for Interactive Physical 3D Scenes
by: Huang, Zhao, et al.
Published: (2025)

MSGNav: Unleashing the Power of Multi-modal 3D Scene Graph for Zero-Shot Embodied Navigation
by: Huang, Xun, et al.
Published: (2025)

SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
by: Singh, Binod, et al.
Published: (2025)

PlaceIt3D: Language-Guided Object Placement in Real 3D Scenes
by: Abdelreheem, Ahmed, et al.
Published: (2025)

Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
by: Li, Haoyuan, et al.
Published: (2025)

PanoSLAM: Panoptic 3D Scene Reconstruction via Gaussian SLAM
by: Chen, Runnan, et al.
Published: (2024)

AgentGrounder: Zero-Shot 3D Visual Pointcloud Grounding using Multimodal Language Models
by: Huynh, Cuong, et al.
Published: (2026)

Unifying Scene Representation and Hand-Eye Calibration with 3D Foundation Models
by: Zhi, Weiming, et al.
Published: (2024)

Rheos: Modelling Continuous Motion Dynamics in Hierarchical 3D Scene Graphs
by: Catalano, Iacopo, et al.
Published: (2026)

GSMem: 3D Gaussian Splatting as Persistent Spatial Memory for Zero-Shot Embodied Exploration and Reasoning
by: Lu, Yiren, et al.
Published: (2026)

Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
by: Kong, Lingdong, et al.
Published: (2024)

IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes
by: Zhang, Haochen, et al.
Published: (2025)

A4-Agent: An Agentic Framework for Zero-Shot Affordance Reasoning
by: Zhang, Zixin, et al.
Published: (2025)

MoD-SLAM: Monocular Dense Mapping for Unbounded 3D Scene Reconstruction
by: Zhou, Heng, et al.
Published: (2024)

OpenLex3D: A Tiered Evaluation Benchmark for Open-Vocabulary 3D Scene Representations
by: Kassab, Christina, et al.
Published: (2025)

Clutt3R-Seg: Sparse-view 3D Instance Segmentation for Language-grounded Grasping in Cluttered Scenes
by: Noh, Jeongho, et al.
Published: (2026)

What Is The Best 3D Scene Representation for Robotics? From Geometric to Foundation Models
by: Deng, Tianchen, et al.
Published: (2025)

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding
by: Wu, Xianjin, et al.
Published: (2026)