HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
- URL: http://arxiv.org/abs/2406.12459v2
- Date: Wed, 30 Oct 2024 12:50:27 GMT
- Title: HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
- Authors: Panwang Pan, Zhuo Su, Chenguo Lin, Zhen Fan, Yongjie Zhang, Zeming Li, Tingting Shen, Yadong Mu, Yebin Liu,
- Abstract summary: HumanSplat predicts the 3D Gaussian Splatting properties of any human from a single input image.
HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis.
- Score: 47.62426718293504
- License:
- Abstract: Despite recent advancements in high-fidelity human reconstruction techniques, the requirements for densely captured images or time-consuming per-instance optimization significantly hinder their applications in broader scenarios. To tackle these issues, we present HumanSplat which predicts the 3D Gaussian Splatting properties of any human from a single input image in a generalizable manner. In particular, HumanSplat comprises a 2D multi-view diffusion model and a latent reconstruction transformer with human structure priors that adeptly integrate geometric priors and semantic features within a unified framework. A hierarchical loss that incorporates human semantic information is further designed to achieve high-fidelity texture modeling and better constrain the estimated multiple views. Comprehensive experiments on standard benchmarks and in-the-wild images demonstrate that HumanSplat surpasses existing state-of-the-art methods in achieving photorealistic novel-view synthesis.
Related papers
- HumanGif: Single-View Human Diffusion with Generative Prior [25.516544735593087]
Motivated by the success of 2D character animation, we propose strong>HumanGif/strong>, a single-view human diffusion model with generative priors.
We formulate the single-view-based 3D human novel view and pose synthesis as a single-view-conditioned human diffusion process.
arXiv Detail & Related papers (2025-02-17T17:55:27Z) - GAS: Generative Avatar Synthesis from a Single Image [54.95198111659466]
We introduce a generalizable and unified framework to synthesize view-consistent and temporally coherent avatars from a single image.
Our approach bridges this gap by combining the reconstruction power of regression-based 3D human reconstruction with the generative capabilities of a diffusion model.
arXiv Detail & Related papers (2025-02-10T19:00:39Z) - GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data [61.05815629606135]
Given a single in-the-wild human photo, it remains a challenging task to reconstruct a high-fidelity 3D human model.
GeneMAN builds upon a comprehensive collection of high-quality human data.
GeneMAN could generate high-quality 3D human models from a single image input, outperforming prior state-of-the-art methods.
arXiv Detail & Related papers (2024-11-27T18:59:54Z) - 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) - PSHuman: Photorealistic Single-view Human Reconstruction using Cross-Scale Diffusion [43.850899288337025]
PSHuman is a novel framework that explicitly reconstructs human meshes utilizing priors from the multiview diffusion model.
It is found that directly applying multiview diffusion on single-view human images leads to severe geometric distortions.
To enhance cross-view body shape consistency of varied human poses, we condition the generative model on parametric models like SMPL-X.
arXiv Detail & Related papers (2024-09-16T10:13:06Z) - HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion [114.15397904945185]
We propose a unified framework, HyperHuman, that generates in-the-wild human images of high realism and diverse layouts.
Our model enforces the joint learning of image appearance, spatial relationship, and geometry in a unified network.
Our framework yields the state-of-the-art performance, generating hyper-realistic human images under diverse scenarios.
arXiv Detail & Related papers (2023-10-12T17:59:34Z) - Progressive Multi-view Human Mesh Recovery with Self-Supervision [68.60019434498703]
Existing solutions typically suffer from poor generalization performance to new settings.
We propose a novel simulation-based training pipeline for multi-view human mesh recovery.
arXiv Detail & Related papers (2022-12-10T06:28:29Z) - HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular
Multi-Person 3D Pose Estimation [54.23770284299979]
This paper introduces a novel form of supervision - Hierarchical Multi-person Ordinal Relations (HMOR)
HMOR encodes interaction information as the ordinal relations of depths and angles hierarchically.
An integrated top-down model is designed to leverage these ordinal relations in the learning process.
The proposed method significantly outperforms state-of-the-art methods on publicly available multi-person 3D pose datasets.
arXiv Detail & Related papers (2020-08-01T07:53:27Z)
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.