GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting

• URL: http://arxiv.org/abs/2603.18912v1
• Date: Thu, 19 Mar 2026 13:50:19 GMT
• Title: GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting
• Abstract summary: GHOST (Gaussian Hand-Object Splatting) is a fast, category-agnostic framework for reconstructing dynamic hand-object interactions.<n>GHOST represents both hands and objects as dense, view-consistent Gaussian discs.<n>GHOST achieves complete, physically consistent, and animatable reconstructions from a single RGB video.
• Score: 13.725244145380563
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding realistic hand-object interactions from monocular RGB videos is essential for AR/VR, robotics, and embodied AI. Existing methods rely on category-specific templates or heavy computation, yet still produce physically inconsistent hand-object alignment in 3D. We introduce GHOST (Gaussian Hand-Object Splatting), a fast, category-agnostic framework for reconstructing dynamic hand-object interactions using 2D Gaussian Splatting. GHOST represents both hands and objects as dense, view-consistent Gaussian discs and introduces three key innovations: (1) a geometric-prior retrieval and consistency loss that completes occluded object regions, (2) a grasp-aware alignment that refines hand translations and object scale to ensure realistic contact, and (3) a hand-aware background loss that prevents penalizing hand-occluded object regions. GHOST achieves complete, physically consistent, and animatable reconstructions from a single RGB video while running an order of magnitude faster than prior category-agnostic methods. Extensive experiments on ARCTIC, HO3D, and in-the-wild datasets demonstrate state-of-the-art accuracy in 3D reconstruction and 2D rendering quality, establishing GHOST as an efficient and robust solution for realistic hand-object interaction modeling. Code is available at https://github.com/ATAboukhadra/GHOST.

Related papers

• Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions [66.64605515970584]
  We present Grasp in Gaussians, a robust method for reconstructing dynamic 3D hand-object interactions from a single monocular video.<n>Our key insight is that accurate and temporally stable hand-object motion can be recovered using a compact Sum-of-Gaussians representation.<n>Experiments on public benchmarks demonstrate that GraG reconstructs temporally coherent hand-object interactions on long sequences 6.4x faster than prior work.
  arXiv  Detail & Related papers  (2026-04-14T16:19:12Z)
• HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images [27.025336665386735]
  We propose a robust, keypoint detector-free approach to estimating hand-object 3D transformations from monocular motion video/images.<n>We further integrate this with a multi-view reconstruction pipeline to accurately recover hand-object 3D shape.<n>Our method, named HOSt3R, is unconstrained, does not rely on pre-scanned object templates or camera intrinsics, and reaches state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-08-22T15:30:40Z)
• SplArt: Articulation Estimation and Part-Level Reconstruction with 3D Gaussian Splatting [15.098827709119087]
  We introduce SplArt, a self-supervised, category-agnostic framework to reconstruct articulated objects and infer kinematics from two sets of posed RGB images.<n>SplArt exploits geometric self-supervision, effectively addressing challenging scenarios without requiring 3D annotations or category-specific priors.<n> Evaluations on established and newly proposed benchmarks, along with applications to real-world scenarios using a handheld RGB camera, demonstrate SplArt's state-of-the-art performance and real-world practicality.
  arXiv  Detail & Related papers  (2025-06-04T05:53:16Z)
• BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting [3.905416830166856]
  We introduce BIGS (Bimanual Interaction 3D Gaussian Splatting), a method that reconstructs 3D Gaussians of hands and an unknown object from a monocular video.<n>Our method achieves the state-of-the-art accuracy on two challenging datasets, in terms of 3D hand pose estimation (MPJPE), 3D object reconstruction (CDh, CDo, F10), and rendering quality (PSNR, SSIM, LPIPS, respectively)
  arXiv  Detail & Related papers  (2025-04-12T06:30:24Z)
• Reconstructing Hand-Held Objects in 3D from Images and Videos [53.277402172488735]
  Given a monocular RGB video, we aim to reconstruct hand-held object geometry in 3D, over time. We present MCC-Hand-Object (MCC-HO), which jointly reconstructs hand and object geometry given a single RGB image. We then prompt a text-to-3D generative model using GPT-4(V) to retrieve a 3D object model that matches the object in the image.
  arXiv  Detail & Related papers  (2024-04-09T17:55:41Z)
• HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting [53.6394928681237]
  holistic understanding of urban scenes based on RGB images is a challenging yet important problem. Our main idea involves the joint optimization of geometry, appearance, semantics, and motion using a combination of static and dynamic 3D Gaussians. Our approach offers the ability to render new viewpoints in real-time, yielding 2D and 3D semantic information with high accuracy.
  arXiv  Detail & Related papers  (2024-03-19T13:39:05Z)
• HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video [70.11702620562889]
  HOLD -- the first category-agnostic method that reconstructs an articulated hand and object jointly from a monocular interaction video. We develop a compositional articulated implicit model that can disentangled 3D hand and object from 2D images. Our method does not rely on 3D hand-object annotations while outperforming fully-supervised baselines in both in-the-lab and challenging in-the-wild settings.
  arXiv  Detail & Related papers  (2023-11-30T10:50:35Z)
• SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction [13.417086460511696]
  We introduce the SHOWMe dataset which consists of 96 videos, annotated with real and detailed hand-object 3D textured meshes. We consider a rigid hand-object scenario, in which the pose of the hand with respect to the object remains constant during the whole video sequence. This assumption allows us to register sub-millimetre-precise groundtruth 3D scans to the image sequences in SHOWMe.
  arXiv  Detail & Related papers  (2023-09-19T16:48:29Z)
• Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements [96.40125818594952]
  We make the first attempt to reconstruct 3D interacting hands from monocular single RGB images. Our method can generate 3D hand meshes with both precise 3D poses and minimal collisions.
  arXiv  Detail & Related papers  (2021-11-01T08:24:10Z)
• RGB2Hands: Real-Time Tracking of 3D Hand Interactions from Monocular RGB Video [76.86512780916827]
  We present the first real-time method for motion capture of skeletal pose and 3D surface geometry of hands from a single RGB camera. In order to address the inherent depth ambiguities in RGB data, we propose a novel multi-task CNN. We experimentally verify the individual components of our RGB two-hand tracking and 3D reconstruction pipeline.
  arXiv  Detail & Related papers  (2021-06-22T12:53:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.