PBDyG: Position Based Dynamic Gaussians for Motion-Aware Clothed Human Avatars

• URL: http://arxiv.org/abs/2412.04433v2
• Date: Fri, 06 Dec 2024 22:51:43 GMT
• Title: PBDyG: Position Based Dynamic Gaussians for Motion-Aware Clothed Human Avatars
• Authors: Shota Sasaki, Jane Wu, Ko Nishino,
• Abstract summary: This paper introduces a novel clothed human model that can be learned from multiview RGB videos. Our method realizes movement-dependent'' cloth deformation via physical simulation. Experiments demonstrate that our method not only accurately reproduces appearance but also enables the reconstruction of avatars wearing highly deformable garments.
• Score: 18.101742122988707
• License:
• Abstract: This paper introduces a novel clothed human model that can be learned from multiview RGB videos, with a particular emphasis on recovering physically accurate body and cloth movements. Our method, Position Based Dynamic Gaussians (PBDyG), realizes ``movement-dependent'' cloth deformation via physical simulation, rather than merely relying on ``pose-dependent'' rigid transformations. We model the clothed human holistically but with two distinct physical entities in contact: clothing modeled as 3D Gaussians, which are attached to a skinned SMPL body that follows the movement of the person in the input videos. The articulation of the SMPL body also drives physically-based simulation of the clothes' Gaussians to transform the avatar to novel poses. In order to run position based dynamics simulation, physical properties including mass and material stiffness are estimated from the RGB videos through Dynamic 3D Gaussian Splatting. Experiments demonstrate that our method not only accurately reproduces appearance but also enables the reconstruction of avatars wearing highly deformable garments, such as skirts or coats, which have been challenging to reconstruct using existing methods.

Related papers

• SimAvatar: Simulation-Ready Avatars with Layered Hair and Clothing [59.44721317364197]
  We introduce SimAvatar, a framework designed to generate simulation-ready clothed 3D human avatars from a text prompt. Our method is the first to produce highly realistic, fully simulation-ready 3D avatars, surpassing the capabilities of current approaches.
  arXiv  Detail & Related papers  (2024-12-12T18:35:26Z)
• PICA: Physics-Integrated Clothed Avatar [30.277983921620663]
  We introduce PICA, a novel representation for high-fidelity animatable clothed human avatars with physics-accurate dynamics, even for loose clothing. Our method achieves high-fidelity rendering of human bodies in complex and novel driving poses, significantly outperforming previous methods under the same settings.
  arXiv  Detail & Related papers  (2024-07-07T10:23:21Z)
• PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations [62.14943588289551]
  We introduce PhysAvatar, a novel framework that combines inverse rendering with inverse physics to automatically estimate the shape and appearance of a human. PhysAvatar reconstructs avatars dressed in loose-fitting clothes under motions and lighting conditions not seen in the training data.
  arXiv  Detail & Related papers  (2024-04-05T21:44:57Z)
• AniDress: Animatable Loose-Dressed Avatar from Sparse Views Using Garment Rigging Model [58.035758145894846]
  We introduce AniDress, a novel method for generating animatable human avatars in loose clothes using very sparse multi-view videos. A pose-driven deformable neural radiance field conditioned on both body and garment motions is introduced, providing explicit control of both parts. Our method is able to render natural garment dynamics that deviate highly from the body and well to generalize to both unseen views and poses.
  arXiv  Detail & Related papers  (2024-01-27T08:48:18Z)
• Deformable 3D Gaussian Splatting for Animatable Human Avatars [50.61374254699761]
  We propose a fully explicit approach to construct a digital avatar from as little as a single monocular sequence. ParDy-Human constitutes an explicit model for realistic dynamic human avatars which requires significantly fewer training views and images. Our avatars learning is free of additional annotations such as Splat masks and can be trained with variable backgrounds while inferring full-resolution images efficiently even on consumer hardware.
  arXiv  Detail & Related papers  (2023-12-22T20:56:46Z)
• GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians [51.46168990249278]
  We present an efficient approach to creating realistic human avatars with dynamic 3D appearances from a single video. GustafAvatar is validated on both the public dataset and our collected dataset.
  arXiv  Detail & Related papers  (2023-12-04T18:55:45Z)
• CaPhy: Capturing Physical Properties for Animatable Human Avatars [44.95805736197971]
  CaPhy is a novel method for reconstructing animatable human avatars with realistic dynamic properties for clothing. We aim for capturing the geometric and physical properties of the clothing from real observations. We combine unsupervised training with physics-based losses and 3D-supervised training using scanned data to reconstruct a dynamic model of clothing.
  arXiv  Detail & Related papers  (2023-08-11T04:01:13Z)
• PERGAMO: Personalized 3D Garments from Monocular Video [6.8338761008826445]
  PERGAMO is a data-driven approach to learn a deformable model for 3D garments from monocular images. We first introduce a novel method to reconstruct the 3D geometry of garments from a single image, and use it to build a dataset of clothing from monocular videos. We show that our method is capable of producing garment animations that match the real-world behaviour, and generalizes to unseen body motions extracted from motion capture dataset.
  arXiv  Detail & Related papers  (2022-10-26T21:15:54Z)
• Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera [49.357174195542854]
  A key challenge of learning the dynamics of the appearance lies in the requirement of a prohibitively large amount of observations. We show that our method can generate a temporally coherent video of dynamic humans for unseen body poses and novel views given a single view video.
  arXiv  Detail & Related papers  (2022-03-24T00:22:03Z)

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.