Generalizable Human Gaussians from Single-View Image

• URL: http://arxiv.org/abs/2406.06050v3
• Date: Fri, 04 Oct 2024 03:52:15 GMT
• Title: Generalizable Human Gaussians from Single-View Image
• Authors: Jinnan Chen, Chen Li, Jianfeng Zhang, Lingting Zhu, Buzhen Huang, Hanlin Chen, Gim Hee Lee,
• Abstract summary: We introduce a single-view generalizable Human Gaussian Model (HGM) Our approach uses a ControlNet to refine rendered back-view images from coarse predicted human Gaussians. To mitigate the potential generation of unrealistic human poses and shapes, we incorporate human priors from the SMPL-X model as a dual branch.
• Score: 52.100234836129786
• License:
• Abstract: In this work, we tackle the task of learning 3D human Gaussians from a single image, focusing on recovering detailed appearance and geometry including unobserved regions. We introduce a single-view generalizable Human Gaussian Model (HGM), which employs a novel generate-then-refine pipeline with the guidance from human body prior and diffusion prior. Our approach uses a ControlNet to refine rendered back-view images from coarse predicted human Gaussians, then uses the refined image along with the input image to reconstruct refined human Gaussians. To mitigate the potential generation of unrealistic human poses and shapes, we incorporate human priors from the SMPL-X model as a dual branch, propagating image features from the SMPL-X volume to the image Gaussians using sparse convolution and attention mechanisms. Given that the initial SMPL-X estimation might be inaccurate, we gradually refine it with our HGM model. We validate our approach on several publicly available datasets. Our method surpasses previous methods in both novel view synthesis and surface reconstruction. Our approach also exhibits strong generalization for cross-dataset evaluation and in-the-wild images.

Related papers

• NovelGS: Consistent Novel-view Denoising via Large Gaussian Reconstruction Model [57.92709692193132]
  NovelGS is a diffusion model for Gaussian Splatting given sparse-view images. We leverage the novel view denoising through a transformer-based network to generate 3D Gaussians.
  arXiv  Detail & Related papers  (2024-11-25T07:57:17Z)
• DiHuR: Diffusion-Guided Generalizable Human Reconstruction [51.31232435994026]
  We introduce DiHuR, a Diffusion-guided model for generalizable Human 3D Reconstruction and view synthesis from sparse, minimally overlapping images. Our method integrates two key priors in a coherent manner: the prior from generalizable feed-forward models and the 2D diffusion prior, and it requires only multi-view image training, without 3D supervision.
  arXiv  Detail & Related papers  (2024-11-16T03:52:23Z)
• HFGaussian: Learning Generalizable Gaussian Human with Integrated Human Features [23.321087432786605]
  We present a novel approach called HFGaussian that can estimate novel views and human features, such as the 3D skeleton, 3D key points, and dense pose, from sparse input images in real time at 25 FPS. We thoroughly evaluate our HFGaussian method against the latest state-of-the-art techniques in human Gaussian splatting and pose estimation, demonstrating its real-time, state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-11-05T13:31:04Z)
• EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Camera Settings [11.248908608011941]
  EVA-Gaussian is a real-time pipeline for 3D human novel view synthesis across diverse camera settings. We introduce an Efficient cross-View Attention (EVA) module to accurately estimate the position of each 3D Gaussian from the source images. We incorporate a powerful anchor loss function for both 3D Gaussian attributes and human face landmarks.
  arXiv  Detail & Related papers  (2024-10-02T11:23:08Z)
• Generalizable Human Gaussians for Sparse View Synthesis [48.47812125126829]
  This paper introduces a new method to learn generalizable human Gaussians that allows photorealistic and accurate view-rendering of a new human subject from a limited set of sparse views. A pivotal innovation of our approach involves reformulating the learning of 3D Gaussian parameters into a regression process defined on the 2D UV space of a human template. Our method outperforms recent methods on both within-dataset generalization as well as cross-dataset generalization settings.
  arXiv  Detail & Related papers  (2024-07-17T17:56:30Z)
• UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling [71.87807614875497]
  We propose UV Gaussians, which models the 3D human body by jointly learning mesh deformations and 2D UV-space Gaussian textures. We collect and process a new dataset of human motion, which includes multi-view images, scanned models, parametric model registration, and corresponding texture maps. Experimental results demonstrate that our method achieves state-of-the-art synthesis of novel view and novel pose.
  arXiv  Detail & Related papers  (2024-03-18T09:03:56Z)
• Template-Free Single-View 3D Human Digitalization with Diffusion-Guided LRM [29.13412037370585]
  We present Human-LRM, a diffusion-guided feed-forward model that predicts the implicit field of a human from a single image. Our method is able to capture human without any template prior, e.g., SMPL, and effectively enhance occluded parts with rich and realistic details.
  arXiv  Detail & Related papers  (2024-01-22T18:08:22Z)
• 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)
• Animatable 3D Gaussians for High-fidelity Synthesis of Human Motions [37.50707388577952]
  We present a novel animatable 3D Gaussian model for rendering high-fidelity free-view human motions in real time. Compared to existing NeRF-based methods, the model owns better capability in high-frequency details without the jittering problem across video frames.
  arXiv  Detail & Related papers  (2023-11-22T14:00:23Z)

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.