arXiv AI
Jul 14
HandFlow: Fully Generative 4D Hand Recovery with Flow Matching
arXiv:2607. 11221v1 Announce Type: cross Abstract: Accurate monocular 4D hand reconstruction remains challenging.
4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction Reconstruction
Related stories
arXiv Computer Vision
1d ago
Open-CHOIR: Open-World Contact-Aware 4D Hand-Object Interaction Reconstruction
arXiv:2605.20992v4 Announce Type: replace Abstract: We ask whether everyday open-world monocular videos can be turned into reusable 4D interaction primitives: articulated hand motion, object shape wi...
Hugging Face Trending Papers
Jul 13
HandFlow: Fully Generative 4D Hand Recovery with Flow Matching
Accurate monocular 4D hand reconstruction remains challenging. Per-frame discriminative regressors lack temporal context and often produce jittery predictions.
arXiv Computer Vision
Sep 30
DynamicHOI: Coupled Dynamics for Physics-aware HOI Reconstruction
arXiv:2609.36454v1 Announce Type: new Abstract: We study hand-object interaction (HOI) reconstruction from monocular RGB videos, where partial observations can produce visually plausible yet mechanic...
arXiv Computer Vision
1d ago
Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos
arXiv:2606.19156v2 Announce Type: replace Abstract: Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite it...
arXiv Computer Vision
1d ago
Video-Conditioned Generative Joint 2D-3D Hand Motion Recovery
The paper introduces JoHan, a generative framework that directly recovers 2D and 3D hand motion from video sequences without intermediate per‑frame pose predictions. By jointly learning temporal dynamics and 2D‑3D correspondence, JoHan generates aligned pose sequences that improve temporal consistency and enable accurate estimation of the hand’s global position and orientation relative to the camera. Experiments on challenging benchmarks show that JoHan achieves higher accuracy and faster performance, producing smoother hand‑motion dynamics while maintaining high per‑frame pose accuracy.
arXiv AI
Jun 29
HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
arXiv:2606. 28215v1 Announce Type: cross Abstract: Extracting dynamic 4D object interactions from massive, in-the-wild monocular videos offers a highly efficient data collection pathway for scaling Embodied AI and training VLAs.
arXiv Computer Vision
Aug 28
Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions
Grasp in Gaussians (GraG) is a fast, robust method for reconstructing dynamic 3D hand‑object interactions from a single monocular video. It leverages pretrained hand and object priors and represents the scene with a compact Sum‑of‑Gaussians (SoG) model, enabling efficient tracking while preserving geometric fidelity. Experiments show GraG achieves temporally coherent reconstructions on long sequences 4.4×–38.9× faster than prior work.
arXiv AI
Oct 1
Exo2EgoHOI: Hand-Object-Interaction Aware Exocentric-to-Egocentric Video Generation
arXiv:2609.38615v1 Announce Type: cross Abstract: Egocentric videos of human manipulation provide valuable visual experience for embodied intelligence, yet collecting such data at scale is costly. Ex...
arXiv AI
Sep 10
From Where to How: Continuous 4D Interaction Forecasting from Egocentric Video
arXiv:2609.08636v1 Announce Type: cross Abstract: Egocentric 4D interaction forecasting aims to anticipate both where future interactions will occur in 3D and how the human body will move to realize...
arXiv Computer Vision
Sep 17
Track, Articulate, Act: Generating Articulation from Casual Human Videos
arXiv:2609.19119v1 Announce Type: new Abstract: Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes...
arXiv AI
Sep 18
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations
FAMOS is a feed‑forward model that predicts movable‑part segmentation and joint parameters from a sparse, unordered set of partial point clouds. It jointly reasons over multiple observations using a Multi‑state Articulation Transformer that alternates state‑wise and global attention, and introduces an observed articulation span objective to supervise motion ranges across inputs. A procedural data generator supplies self‑annotated assets for training, and experiments on PartNet‑Mobility, ACD, and ArtiCraft‑10K show consistent improvements over existing feed‑forward and optimization‑based baselines.