Imagen de Portada

3DAxisPrompt: Promoting the 3D Grounding and Reasoning in GPT-4o

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Dingning, Wang, Cheng, Gao, Peng, Zhang, Renrui, Ma, Xinzhu, Meng, Yuan, Wang, Zhihui
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models
por: Liu, Dingning, et al.
Publicado: (2024)

Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection
por: Zhang, Yinmin, et al.
Publicado: (2021)

Referring Video Object Segmentation with Cross-Modality Proxy Queries
por: Sun, Baoli, et al.
Publicado: (2025)

Propagating Sparse Depth via Depth Foundation Model for Out-of-Distribution Depth Completion
por: Chen, Shenglun, et al.
Publicado: (2025)

Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition
por: Sun, Baoli, et al.
Publicado: (2025)

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

TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction
por: Zhang, Xuying, et al.
Publicado: (2024)

3D Object Detection from Images for Autonomous Driving: A Survey
por: Ma, Xinzhu, et al.
Publicado: (2022)

R2G: Reasoning to Ground in 3D Scenes
por: Li, Yixuan, et al.
Publicado: (2024)

Reasoning Matters for 3D Visual Grounding
por: Huang, Hsiang-Wei, et al.
Publicado: (2026)

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models
por: Wang, Yuxin, et al.
Publicado: (2025)

Point2Primitive: CAD Reconstruction from Point Cloud by Direct Primitive Prediction
por: Ma, Xinzhu, et al.
Publicado: (2025)

Know3D: Prompting 3D Generation with Knowledge from Vision-Language Models
por: Chen, Wenyue, et al.
Publicado: (2026)

Towards Efficient and Intelligent Laser Weeding: Method and Dataset for Weed Stem Detection
por: Liu, Dingning, et al.
Publicado: (2025)

Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
por: Cheng, Xinhua, et al.
Publicado: (2023)

MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding
por: Zheng, Henry, et al.
Publicado: (2026)

TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt
por: Yang, Jiahui, et al.
Publicado: (2024)

SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
por: Li, Wanhua, et al.
Publicado: (2024)

SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
por: Ma, Wufei, et al.
Publicado: (2025)

SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
por: Ma, Chenyang, et al.
Publicado: (2024)

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding
por: Gao, Xianqiang, et al.
Publicado: (2024)

Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
por: Meng, Jiahao, et al.
Publicado: (2025)

GPT-4V-AD: Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection
por: Zhang, Jiangning, et al.
Publicado: (2023)

ProxyTransformation: Preshaping Point Cloud Manifold With Proxy Attention For 3D Visual Grounding
por: Peng, Qihang, et al.
Publicado: (2025)

Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation
por: Jia, Yueru, et al.
Publicado: (2024)

Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning without 3D Annotations
por: Yuan, Zhihao, et al.
Publicado: (2025)

No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation
por: Zhu, Xiangyang, et al.
Publicado: (2024)

ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning
por: Liu, Zhenyang, et al.
Publicado: (2025)

NTO3D: Neural Target Object 3D Reconstruction with Segment Anything
por: Wei, Xiaobao, et al.
Publicado: (2023)

ASAP: Advancing Semantic Alignment Promotes Multi-Modal Manipulation Detecting and Grounding
por: Zhang, Zhenxing, et al.
Publicado: (2024)

LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory
por: Cao, Jianbao, et al.
Publicado: (2026)

SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation
por: Li, Yuan, et al.
Publicado: (2026)

Training-free Regional Prompting for Diffusion Transformers
por: Chen, Anthony, et al.
Publicado: (2024)

Prompt fidelity of ChatGPT4o / Dall-E3 text-to-image visualisations
por: Spennemann, Dirk HR
Publicado: (2025)

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
por: Jin, Zhao, et al.
Publicado: (2025)

PF3Det: A Prompted Foundation Feature Assisted Visual LiDAR 3D Detector
por: Li, Kaidong, et al.
Publicado: (2025)

OpenGround: Active Cognition-based Reasoning for Open-World 3D Visual Grounding
por: Huang, Wenyuan, et al.
Publicado: (2025)

Boosting MLLM Spatial Reasoning with Geometrically Referenced 3D Scene Representations
por: Yuan, Jiangye, et al.
Publicado: (2026)

ChangingGrounding: 3D Visual Grounding in Changing Scenes
por: Hu, Miao, et al.
Publicado: (2025)

GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models
por: Qi, Zhangyang, et al.
Publicado: (2025)