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.
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.
Related stories
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
2d ago
ACE-Ego-Hand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery
arXiv:2608.20308v2 Announce Type: replace Abstract: Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe ob...
arXiv Computer Vision
Aug 21
DreamHand: Repurposing Video Diffusion Models for Occlusion-Robust Egocentric 3D Hand Motion Recovery
arXiv:2608. 20308v1 Announce Type: new Abstract: Egocentric video offers scalable manipulation data for embodied AI, yet recovering metric 3D hand trajectories remains challenging due to severe object occlusion and frequent out-of-sight gaps.
Hugging Face Trending Papers
Jun 9
ManiSplat: Manipulation Trajectory Synthesis from Monocular Video via Decoupled 3D Gaussian Splatting
Reconstructing dynamic and interactive 3D scenes from real-world observations remains a fundamental challenge in computer vision and robotics. While recent advances in 3D Gaussian Splatting have enabled high-fidelity static reconstruction, extending it to interactive environments with articulated robots and manipulable objects remains difficult due to complex contact interactions and abrupt pose changes.
arXiv AI
Jun 19
Human Universal Grasping
arXiv:2606. 17054v1 Announce Type: cross Abstract: Humans can grasp objects effortlessly, whereas multi-fingered robots are far from this level of generality.
arXiv AI
Aug 25
TransHands: Repurposing Human Pose Encoders as Hand Pose Encoders
arXiv:2608.22341v1 Announce Type: cross Abstract: Lifting 3D hand poses from 2D monocular representations remains challenging due to the limited availability of large-scale, diverse 3D-annotated hand...
arXiv AI
Jul 21
ReViV: Reconstructing the Viewer and the View in 4D from Monocular Egocentric Video
arXiv:2607. 17790v1 Announce Type: cross Abstract: Egocentric devices, such as wearable front-facing cameras, provide a unique perspective for capturing the continuous interaction between a human viewer and the surrounding environment.
Hugging Face Trending Papers
Jul 8
GIRAF: Towards Generalizable Human Interactions with Articulated Objects
Synthesizing realistic full-body human interactions with articulated objects is a fundamental challenge for embodied AI and graphics, with applications in robotics training and virtual agents. Existing models remain limited: some focus on simple activities with static objects, while others restrict attention to hand-only manipulation.
arXiv Computer Vision
Aug 27
4DStreamCtrl: Interactive Video Generation with Online 4D Control
The paper introduces 4DStreamCtrl, a system that unifies camera motion, object trajectories, and depth into a single 3D point‑track representation, enabling joint control, depth editing, and motion transfer in a single forward pass. By mining in‑the‑wild video for 3D motion supervision and encoding it with a lightweight Geometric Motion Head, the authors train a causal streaming student that can generate arbitrarily long videos in just four denoising steps, achieving 20 FPS on a single high‑end GPU for 480p video. This approach outperforms prior camera‑only, 2D, and offline‑3D methods in motion‑control precision while maintaining temporal coherence over hundreds of frames, thereby enabling interactive 4D‑controllable streaming generation for the first time.
arXiv Computer Vision
Aug 27
Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos
Forge4D is a feed‑forward model that reconstructs temporally aligned 4D human representations from uncalibrated sparse‑view videos, enabling both novel view and novel time synthesis. It achieves this by jointly streaming 3D Gaussian reconstruction with dense motion prediction, using learnable state tokens for temporal consistency and a self‑supervised retargeting loss for motion prediction. Extensive experiments confirm its effectiveness on in‑domain and out‑of‑domain datasets.
arXiv Computer Vision
3d ago
GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image
arXiv:2608.28386v1 Announce Type: new Abstract: Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic o...