Imagen de Portada

SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidance

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xia, Qi, Cong, Peishan, Wang, Ziyi, Sun, Yujing, Sun, Qin, Zhu, Xinge, Ye, Mao, Yang, Ruigang, Ma, Yuexin
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SemGeoMo: Dynamic Contextual Human Motion Generation with Semantic and Geometric Guidance
por: Cong, Peishan, et al.
Publicado: (2025)

ReMoGen: Real-time Human Interaction-to-Reaction Generation via Modular Learning from Diverse Data
por: Ye, Yaoqin, et al.
Publicado: (2026)

Controllable Video Object Insertion via Multiview Priors
por: Qi, Xia, et al.
Publicado: (2026)

LaserHuman: Language-guided Scene-aware Human Motion Generation in Free Environment
por: Cong, Peishan, et al.
Publicado: (2024)

HUMOF: Human Motion Forecasting in Interactive Social Scenes
por: Sun, Caiyi, et al.
Publicado: (2025)

Gait Recognition in Large-scale Free Environment via Single LiDAR
por: Han, Xiao, et al.
Publicado: (2022)

EvolvingGrasp: Evolutionary Grasp Generation via Efficient Preference Alignment
por: Zhu, Yufei, et al.
Publicado: (2025)

HUNTER: Unsupervised Human-centric 3D Detection via Transferring Knowledge from Synthetic Instances to Real Scenes
por: Yao, Yichen, et al.
Publicado: (2024)

WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language
por: Lin, Zhenxiang, et al.
Publicado: (2023)

A Unified Framework for Human-centric Point Cloud Video Understanding
por: Xu, Yiteng, et al.
Publicado: (2024)

StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset
por: Huo, Chaofan, et al.
Publicado: (2024)

RHINO: Reconstructing Human Interactions with Novel Objects from Monocular Videos
por: Xue, Lixin, et al.
Publicado: (2026)

Towards Practical Human Motion Prediction with LiDAR Point Clouds
por: Han, Xiao, et al.
Publicado: (2024)

ReAL-AD: Towards Human-Like Reasoning in End-to-End Autonomous Driving
por: Lu, Yuhang, et al.
Publicado: (2025)

SymBridge: A Human-in-the-Loop Cyber-Physical Interactive System for Adaptive Human-Robot Symbiosis
por: Chen, Haoran, et al.
Publicado: (2025)

Monocular Human-Object Reconstruction in the Wild
por: Huo, Chaofan, et al.
Publicado: (2024)

Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction
por: Wen, Boran, et al.
Publicado: (2025)

Sparkle: A Robust and Versatile Representation for Point Cloud based Human Motion Capture
por: Ren, Yiming, et al.
Publicado: (2026)

Exploring Textual Semantics Diversity for Image Transmission in Semantic Communication Systems using Visual Language Model
por: Huang, Peishan, et al.
Publicado: (2025)

FreeCap: Hybrid Calibration-Free Motion Capture in Open Environments
por: Xue, Aoru, et al.
Publicado: (2024)

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens
por: Zhong, Yiming, et al.
Publicado: (2025)

Diffusion-based Human Motion Style Transfer with Semantic Guidance
por: Hu, Lei, et al.
Publicado: (2024)

Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video
por: Guo, Jiaxin, et al.
Publicado: (2025)

Learning to Adapt SAM for Segmenting Cross-domain Point Clouds
por: Peng, Xidong, et al.
Publicado: (2023)

Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation
por: Cong, Wei, et al.
Publicado: (2024)

Extreme Two-View Geometry From Object Poses with Diffusion Models
por: Sun, Yujing, et al.
Publicado: (2024)

Generalizable Single-view Object Pose Estimation by Two-side Generating and Matching
por: Sun, Yujing, et al.
Publicado: (2024)

SocialCircle+: Learning the Angle-based Conditioned Interaction Representation for Pedestrian Trajectory Prediction
por: Wong, Conghao, et al.
Publicado: (2024)

SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction
por: Wong, Conghao, et al.
Publicado: (2023)

Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception
por: Garcia, Kathy, et al.
Publicado: (2025)

Follow My Hold: Hand-Object Interaction Reconstruction through Geometric Guidance
por: Aytekin, Ayce Idil, et al.
Publicado: (2025)

Time Travel: LLM-Assisted Semantic Behavior Localization with Git Bisect
por: Wang, Yujing, et al.
Publicado: (2025)

Exploiting Spatial-Temporal Context for Interacting Hand Reconstruction on Monocular RGB Video
por: Zhao, Weichao, et al.
Publicado: (2023)

OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
por: Lu, Yuhang, et al.
Publicado: (2023)

Sufficient conditions for the variation of toughness under the distance spectral in graphs involving minimum degree
por: Li, Peishan
Publicado: (2025)

DressRecon: Freeform 4D Human Reconstruction from Monocular Video
por: Tan, Jeff, et al.
Publicado: (2024)

Who Walks With You Matters: Perceiving Social Interactions with Groups for Pedestrian Trajectory Prediction
por: Zou, Ziqian, et al.
Publicado: (2024)

ESP: Extro-Spective Prediction for Long-term Behavior Reasoning in Emergency Scenarios
por: Wang, Dingrui, et al.
Publicado: (2024)

DeFakeQ: Enabling Real-Time Deepfake Detection on Edge Devices via Adaptive Bidirectional Quantization
por: Li, Xiangyu, et al.
Publicado: (2026)

UniDemoiré: Towards Universal Image Demoiréing with Data Generation and Synthesis
por: Yang, Zemin, et al.
Publicado: (2025)