paper-with-me

hand-object pose

2개 벤치마크 · 논문 39편 · 이 태스크의 논문 보기 →

Benchmarks

DexYCB

결과 72개

HO-3D v2

결과 72개

Most implemented

Papers

SparseCtrl-HOI: Sparse Temporal Control for Human-Object Interaction Video Generation

2026-07-07 · Shenbo Xie, Mingrui Cai, Xu Yang, Yifei Liu 외 arxiv

Human-Object Interaction (HOI) video generation aims to synthesize realistic videos of humans manipulating diverse objects, serving as a promising avenue for AI-driven live streaming e-commerce. A primary obstacle in thi…

Motion SynthesisVideo Generationhand-object pose

Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation

2026-06-29 · Siddhant Bansal, Zhifan Zhu, Shashank Tripathi, Jiahe Zhao 외 arxiv

Estimating accurate 3D hand-object pose from in-the-wild egocentric RGB remains challenging due to severe occlusions and ambiguous contact. Existing learning-based methods often struggle to generalise to in-the-wild scen…

hand-object posePose Estimation

GenHOI: Generalized Hand-Object Pose Estimation with Occlusion Awareness

2026-03-19 · Hui Yang, Wei Sun, Jian Liu, Jian Xiao 외 arxiv

Generalized 3D hand-object pose estimation from a single RGB image remains challenging due to the large variations in object appearances and interaction patterns, especially under heavy occlusion. We propose GenHOI, a fr…

hand-object posePose EstimationPoint Clouds

VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation

2025-11-15 · Jun Zhou, Chi Xu, Kaifeng Tang, Yuting Ge 외 arxiv

Estimating the 3D poses of hands and objects from a single RGB image is a fundamental yet challenging problem, with broad applications in augmented reality and human-computer interaction. Existing methods largely rely on…

Representation Learninghand-object pose

Towards Realistic Hand-Object Interaction with Gravity-Field Based Diffusion Bridge

2025-09-03 · Miao Xu, Xiangyu Zhu, Xusheng Liang, Zidu Wang 외 arxiv

Existing reconstruction or hand-object pose estimation methods are capable of producing coarse interaction states. However, due to the complex and diverse geometry of both human hands and objects, these approaches often …

hand-object pose

Occlusion-Aware 3D Hand-Object Pose Estimation with Masked AutoEncoders

2025-06-12 · Hui Yang, Wei Sun, Jian Liu, Jin Zheng 외

Hand-object pose estimation from monocular RGB images remains a significant challenge mainly due to the severe occlusions inherent in hand-object interactions. Existing methods do not sufficiently explore global structur…

hand-object poseObjectPose Estimation

전체 39편 보기 →