Copertina

Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Baik, Sangwon, Kim, Gunhee, Choi, Mingi, Joo, Hanbyul
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models
di: Baik, Sangwon, et al.
Pubblicazione: (2025)

DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Models
di: Kim, Hyeonwoo, et al.
Pubblicazione: (2025)

Learning to Generate Human-Human-Object Interactions from Textual Descriptions
di: Na, Jeonghyeon, et al.
Pubblicazione: (2025)

DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation
di: Kim, Hyeonwoo, et al.
Pubblicazione: (2026)

ParaHome: Parameterizing Everyday Home Activities Towards 3D Generative Modeling of Human-Object Interactions
di: Kim, Jeonghwan, et al.
Pubblicazione: (2024)

Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
di: Cha, Hyunsoo, et al.
Pubblicazione: (2025)

Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models
di: Kim, Hyeonwoo, et al.
Pubblicazione: (2024)

HRDexDB: A Large-Scale Dataset of Dexterous Human and Robotic Hand Grasps
di: Lim, Jongbin, et al.
Pubblicazione: (2026)

Target-Aware Video Diffusion Models
di: Kim, Taeksoo, et al.
Pubblicazione: (2025)

Guess The Unseen: Dynamic 3D Scene Reconstruction from Partial 2D Glimpses
di: Lee, Inhee, et al.
Pubblicazione: (2024)

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
di: Cha, Hyunsoo, et al.
Pubblicazione: (2024)

OmniRobotHome: A Multi-Camera Platform for Real-Time Multiadic Human-Robot Interaction
di: Lee, Junyoung, et al.
Pubblicazione: (2026)

GraspDiffusion: Synthesizing Realistic Whole-body Hand-Object Interaction
di: Kwon, Patrick, et al.
Pubblicazione: (2024)

OmniEgoCap: Camera-Agnostic Sequence-Level Egocentric Motion Reconstruction
di: Cho, Kyungwon, et al.
Pubblicazione: (2025)

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
di: Cha, Hyunsoo, et al.
Pubblicazione: (2026)

PERSE: Personalized 3D Generative Avatars from A Single Portrait
di: Cha, Hyunsoo, et al.
Pubblicazione: (2024)

VLM6D: VLM based 6Dof Pose Estimation based on RGB-D Images
di: Sarowar, Md Selim, et al.
Pubblicazione: (2025)

Mocap Everyone Everywhere: Lightweight Motion Capture With Smartwatches and a Head-Mounted Camera
di: Lee, Jiye, et al.
Pubblicazione: (2024)

Dexterous World Models
di: Kim, Byungjun, et al.
Pubblicazione: (2025)

GALA: Generating Animatable Layered Assets from a Single Scan
di: Kim, Taeksoo, et al.
Pubblicazione: (2024)

LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning
di: Wang, Kaihong, et al.
Pubblicazione: (2025)

MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations
di: Bae, Kyungho, et al.
Pubblicazione: (2025)

TIE-KD: Teacher-Independent and Explainable Knowledge Distillation for Monocular Depth Estimation
di: Choi, Sangwon, et al.
Pubblicazione: (2024)

Mask6D: Masked Pose Priors For 6D Object Pose Estimation
di: Xie, Yuechen, et al.
Pubblicazione: (2025)

THE-Pose: Topological Prior with Hybrid Graph Fusion for Estimating Category-Level 6D Object Pose
di: Lee, Eunho, et al.
Pubblicazione: (2025)

GMFlow: Global Motion-Guided Recurrent Flow for 6D Object Pose Estimation
di: Liu, Xin, et al.
Pubblicazione: (2024)

Event6D: Event-based Novel Object 6D Pose Tracking
di: Kang, Jae-Young, et al.
Pubblicazione: (2026)

RefPose: Leveraging Reference Geometric Correspondences for Accurate 6D Pose Estimation of Unseen Objects
di: Kim, Jaeguk, et al.
Pubblicazione: (2025)

SmartAvatar: Text- and Image-Guided Human Avatar Generation with VLM AI Agents
di: Huang-Menders, Alexander, et al.
Pubblicazione: (2025)

HairCUP: Hair Compositional Universal Prior for 3D Gaussian Avatars
di: Kim, Byungjun, et al.
Pubblicazione: (2025)

Human-Object Interaction via Automatically Designed VLM-Guided Motion Policy
di: Deng, Zekai, et al.
Pubblicazione: (2025)

Dynamic VLM-Guided Negative Prompting for Diffusion Models
di: Chang, Hoyeon, et al.
Pubblicazione: (2025)

Pose-Guided Residual Refinement for Interpretable Text-to-Motion Generation and Editing
di: Jeong, Sukhyun, et al.
Pubblicazione: (2025)

TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer
di: Lin, Xiao, et al.
Pubblicazione: (2023)

AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
di: Kang, Bin, et al.
Pubblicazione: (2026)

Exploring 6D Object Pose Estimation with Deformation
di: Liu, Zhiqiang, et al.
Pubblicazione: (2026)

GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects
di: Moon, Sungphill, et al.
Pubblicazione: (2024)

GS2Pose: Two-stage 6D Object Pose Estimation Guided by Gaussian Splatting
di: Mei, Jilan, et al.
Pubblicazione: (2024)

PhysPose: Refining 6D Object Poses with Physical Constraints
di: Malenický, Martin, et al.
Pubblicazione: (2025)

Gaussian Blending: Rethinking Alpha Blending in 3D Gaussian Splatting
di: Koo, Junseo, et al.
Pubblicazione: (2025)