Cover Image

Masked Modeling for Human Motion Recovery Under Occlusions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Qian, Zhiyin, Zhang, Siwei, Bhatnagar, Bharat Lal, Bogo, Federica, Tang, Siyu
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RoHM: Robust Human Motion Reconstruction via Diffusion
by: Zhang, Siwei, et al.
Published: (2024)

Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation
by: Xie, Xianghui, et al.
Published: (2023)

3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
by: Qian, Zhiyin, et al.
Published: (2023)

GEARS: Local Geometry-aware Hand-object Interaction Synthesis
by: Zhou, Keyang, et al.
Published: (2024)

SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction
by: Mihajlovic, Marko, et al.
Published: (2024)

FORCE: Physics-aware Human-object Interaction
by: Zhang, Xiaohan, et al.
Published: (2024)

OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression
by: Li, Zhe, et al.
Published: (2025)

Discriminative-Generative Synergy for Occlusion Robust 3D Human Mesh Recovery
by: Liu, Yang, et al.
Published: (2026)

Text-driven Human Motion Generation with Motion Masked Diffusion Model
by: Chen, Xingyu
Published: (2024)

ReMoMask: Retrieval-Augmented Masked Motion Generation
by: Li, Zhengdao, et al.
Published: (2025)

MEGA: Masked Generative Autoencoder for Human Mesh Recovery
by: Fiche, Guénolé, et al.
Published: (2024)

MoPO: Incorporating Motion Prior for Occluded Human Mesh Recovery
by: Tang, Tao, et al.
Published: (2026)

MoSA: Motion-Coherent Human Video Generation via Structure-Appearance Decoupling
by: Wang, Haoyu, et al.
Published: (2025)

HumanMM: Global Human Motion Recovery from Multi-shot Videos
by: Zhang, Yuhong, et al.
Published: (2025)

DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control
by: Zhao, Kaifeng, et al.
Published: (2024)

ATLAS: Decoupling Skeletal and Shape Parameters for Expressive Parametric Human Modeling
by: Park, Jinhyung, et al.
Published: (2025)

One-shot Human Motion Transfer via Occlusion-Robust Flow Prediction and Neural Texturing
by: Ji, Yuzhu, et al.
Published: (2024)

Occlusion-Aware 3D Motion Interpretation for Abnormal Behavior Detection
by: Li, Su, et al.
Published: (2024)

MAFS: Masked Autoencoder for Infrared-Visible Image Fusion and Semantic Segmentation
by: Wang, Liying, et al.
Published: (2025)

Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery
by: Yang, Fengyuan, et al.
Published: (2024)

Towards Geometry-Aware and Motion-Guided Video Human Mesh Recovery
by: Chen, Hongjun, et al.
Published: (2026)

A Taxonomy of Structure from Motion Methods
by: Arrigoni, Federica
Published: (2025)

GPT-4 for Occlusion Order Recovery
by: Saleh, Kaziwa, et al.
Published: (2025)

Validation of Human Pose Estimation and Human Mesh Recovery for Extracting Clinically Relevant Motion Data from Videos
by: Armstrong, Kai, et al.
Published: (2025)

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

Benchmarking 3D Human Pose Estimation Models under Occlusions
by: Lino, Filipa, et al.
Published: (2025)

Multimodal Object Detection Under Sparse Forest-Canopy Occlusion
by: Jain, Nitik, et al.
Published: (2026)

Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders
by: Yang, Hui, et al.
Published: (2025)

KMM: Key Frame Mask Mamba for Extended Motion Generation
by: Zhang, Zeyu, et al.
Published: (2024)

Team-Aware Football Player Tracking with SAM: An Appearance-Based Approach to Occlusion Recovery
by: Ranasinghe, Chamath, et al.
Published: (2025)

DeclutterNeRF: Generative-Free 3D Scene Recovery for Occlusion Removal
by: Liu, Wanzhou, et al.
Published: (2025)

UVOSAM: A Mask-free Paradigm for Unsupervised Video Object Segmentation via Segment Anything Model
by: Zhang, Zhenghao, et al.
Published: (2023)

VolumetricSMPL: A Neural Volumetric Body Model for Efficient Interactions, Contacts, and Collisions
by: Mihajlovic, Marko, et al.
Published: (2025)

Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation
by: Li, Chenyu, et al.
Published: (2024)

MaskControl: Spatio-Temporal Control for Masked Motion Synthesis
by: Pinyoanuntapong, Ekkasit, et al.
Published: (2024)

OpenMoCap: Rethinking Optical Motion Capture under Real-world Occlusion
by: Qian, Chen, et al.
Published: (2025)

Stable Diffusion-Based Approach for Human De-Occlusion
by: Noh, Seung Young, et al.
Published: (2025)

Wild2Avatar: Rendering Humans Behind Occlusions
by: Xiang, Tiange, et al.
Published: (2023)

RHOBIN Challenge: Reconstruction of Human Object Interaction
by: Xie, Xianghui, et al.
Published: (2024)

DogMo: A Large-Scale Multi-View RGB-D Dataset for 4D Canine Motion Recovery
by: Wang, Zan, et al.
Published: (2025)