Copertina

R2G: Reasoning to Ground in 3D Scenes

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Yixuan, Wang, Zan, Liang, Wei
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation
di: Zhu, Ziyu, et al.
Pubblicazione: (2025)

Grounding by Remembering: Cross-Scene and In-Scene Memory for 3D Functional Affordances
di: Wang, Qirui, et al.
Pubblicazione: (2026)

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

SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes
di: Linghu, Xiongkun, et al.
Pubblicazione: (2025)

Task-oriented Sequential Grounding and Navigation in 3D Scenes
di: Zhang, Zhuofan, et al.
Pubblicazione: (2024)

3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding
di: Huang, Ting, et al.
Pubblicazione: (2025)

Grounding 3D Scene Affordance From Egocentric Interactions
di: Liu, Cuiyu, et al.
Pubblicazione: (2024)

Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale
di: Wei, Dongxu, et al.
Pubblicazione: (2026)

Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
di: Ran, Xingjian, et al.
Pubblicazione: (2025)

UniGround: Universal 3D Visual Grounding via Training-Free Scene Parsing
di: Zhang, Jiaxi, et al.
Pubblicazione: (2026)

A3R: Agentic Affordance Reasoning via Cross-Dimensional Evidence in 3D Gaussian Scenes
di: Li, Di, et al.
Pubblicazione: (2026)

Human Motion Estimation with Everyday Wearables
di: Zhu, Siqi, et al.
Pubblicazione: (2025)

SceneTeract: Agentic Functional Affordances and VLM Grounding in 3D Scenes
di: Maillard, Léopold, et al.
Pubblicazione: (2026)

Ground-R1: Incentivizing Grounded Visual Reasoning via Reinforcement Learning
di: Cao, Meng, et al.
Pubblicazione: (2025)

SGR3 Model: Scene Graph Retrieval-Reasoning Model in 3D
di: Wang, Zirui, et al.
Pubblicazione: (2026)

View-on-Graph: Zero-shot 3D Visual Grounding via Vision-Language Reasoning on Scene Graphs
di: Liu, Yuanyuan, et al.
Pubblicazione: (2025)

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

Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs
di: Huang, Jincai, et al.
Pubblicazione: (2026)

LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation
di: Yang, Shuai, et al.
Pubblicazione: (2024)

D$^2$USt3R: Enhancing 3D Reconstruction for Dynamic Scenes
di: Han, Jisang, et al.
Pubblicazione: (2025)

Ground4D: Spatially-Grounded Feedforward 4D Reconstruction for Unstructured Off-Road Scenes
di: Wang, Shuo, et al.
Pubblicazione: (2026)

SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment
di: Xu, Qi, et al.
Pubblicazione: (2025)

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes
di: Wang, Tianxu, et al.
Pubblicazione: (2025)

GeoWeaver: Grounding Visual Tokens with Geometric Evidence before Scene Reasoning
di: Miao, Deshui, et al.
Pubblicazione: (2026)

R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding
di: Wu, Qirui, et al.
Pubblicazione: (2024)

Multimodal 3D Reasoning Segmentation with Complex Scenes
di: Jiang, Xueying, et al.
Pubblicazione: (2024)

DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding
di: Ge, Luzhou, et al.
Pubblicazione: (2026)

SpatialReasoner: Active Perception for Large-Scale 3D Scene Understanding
di: Zheng, Hongpei, et al.
Pubblicazione: (2025)

PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding
di: Jung, Seongmin, et al.
Pubblicazione: (2025)

H2G: Hierarchy-Aware Hyperbolic Grouping for 3D Scenes
di: Ko, ByungHa, et al.
Pubblicazione: (2026)

PhyScene3D: Physically Consistent Interactive 3D Tabletop Scene Generation
di: Chen, Weixing, et al.
Pubblicazione: (2026)

SAS: Segment Any 3D Scene with Integrated 2D Priors
di: Li, Zhuoyuan, et al.
Pubblicazione: (2025)

RefFusion: Reference Adapted Diffusion Models for 3D Scene Inpainting
di: Mirzaei, Ashkan, et al.
Pubblicazione: (2024)

A Unified Framework for 3D Scene Understanding
di: Xu, Wei, et al.
Pubblicazione: (2024)

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

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding
di: Chang, Chun-Peng, et al.
Pubblicazione: (2024)

Toward Scene Graph and Layout Guided Complex 3D Scene Generation
di: Huang, Yu-Hsiang, et al.
Pubblicazione: (2024)

From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coaching
di: Ji, Yuyang, et al.
Pubblicazione: (2026)

Open-Vocabulary Indoor Object Grounding with 3D Hierarchical Scene Graph
di: Linok, Sergey, et al.
Pubblicazione: (2025)