Bundle Adjusted Gaussian Avatars Deblurring
- URL: http://arxiv.org/abs/2411.16758v1
- Date: Sun, 24 Nov 2024 10:03:24 GMT
- Title: Bundle Adjusted Gaussian Avatars Deblurring
- Authors: Muyao Niu, Yifan Zhan, Qingtian Zhu, Zhuoxiao Li, Wei Wang, Zhihang Zhong, Xiao Sun, Yinqiang Zheng,
- Abstract summary: We propose a 3D-aware, physics-oriented model of blur formation attributable to human movement and a 3D human motion model to clarify ambiguities found in motion-induced blurry images.
We have established benchmarks for this task through a synthetic dataset derived from existing multi-view captures, alongside a real-captured dataset acquired through a 360-degree synchronous hybrid-exposure camera system.
- Score: 31.718130377229482
- License:
- Abstract: The development of 3D human avatars from multi-view videos represents a significant yet challenging task in the field. Recent advancements, including 3D Gaussian Splattings (3DGS), have markedly progressed this domain. Nonetheless, existing techniques necessitate the use of high-quality sharp images, which are often impractical to obtain in real-world settings due to variations in human motion speed and intensity. In this study, we attempt to explore deriving sharp intrinsic 3D human Gaussian avatars from blurry video footage in an end-to-end manner. Our approach encompasses a 3D-aware, physics-oriented model of blur formation attributable to human movement, coupled with a 3D human motion model to clarify ambiguities found in motion-induced blurry images. This methodology facilitates the concurrent learning of avatar model parameters and the refinement of sub-frame motion parameters from a coarse initialization. We have established benchmarks for this task through a synthetic dataset derived from existing multi-view captures, alongside a real-captured dataset acquired through a 360-degree synchronous hybrid-exposure camera system. Comprehensive evaluations demonstrate that our model surpasses existing baselines.
Related papers
- Deblur-Avatar: Animatable Avatars from Motion-Blurred Monocular Videos [64.10307207290039]
De-Avatar is a novel framework for modeling high-fidelity, animatable 3D human avatars from motion-blurred monocular video inputs.
arXiv Detail & Related papers (2025-01-23T02:31:57Z) - 3D$^2$-Actor: Learning Pose-Conditioned 3D-Aware Denoiser for Realistic Gaussian Avatar Modeling [37.11454674584874]
We introduce 3D$2$-Actor, a pose-conditioned 3D-aware human modeling pipeline that integrates 2D denoising and 3D rectifying steps.
Experimental results demonstrate that 3D$2$-Actor excels in high-fidelity avatar modeling and robustly generalizes to novel poses.
arXiv Detail & Related papers (2024-12-16T09:37:52Z) - AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction [26.82525451095629]
We propose a robust method for 3D reconstruction of inconsistent images, enabling real-time rendering during inference.
We recast the reconstruction problem as a 4D task and introduce an efficient 3D modeling approach using 4D Gaussian Splatting.
Experiments demonstrate that our method achieves photorealistic, real-time animation of 3D human avatars from in-the-wild images.
arXiv Detail & Related papers (2024-12-03T18:55:39Z) - DreamDance: Animating Human Images by Enriching 3D Geometry Cues from 2D Poses [57.17501809717155]
We present DreamDance, a novel method for animating human images using only skeleton pose sequences as conditional inputs.
Our key insight is that human images naturally exhibit multiple levels of correlation.
We construct the TikTok-Dance5K dataset, comprising 5K high-quality dance videos with detailed frame annotations.
arXiv Detail & Related papers (2024-11-30T08:42:13Z) - NPGA: Neural Parametric Gaussian Avatars [46.52887358194364]
We propose a data-driven approach to create high-fidelity controllable avatars from multi-view video recordings.
We build our method around 3D Gaussian splatting for its highly efficient rendering and to inherit the topological flexibility of point clouds.
We evaluate our method on the public NeRSemble dataset, demonstrating that NPGA significantly outperforms the previous state-of-the-art avatars on the self-reenactment task by 2.6 PSNR.
arXiv Detail & Related papers (2024-05-29T17:58:09Z) - Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance [25.346255905155424]
We introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework.
By representing the 3D human parametric model as the motion guidance, we can perform parametric shape alignment of the human body between the reference image and the source video motion.
Our approach also exhibits superior generalization capabilities on the proposed in-the-wild dataset.
arXiv Detail & Related papers (2024-03-21T18:52:58Z) - 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) - Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based
Motion Refinement [65.08165593201437]
We explore egocentric whole-body motion capture using a single fisheye camera, which simultaneously estimates human body and hand motion.
This task presents significant challenges due to the lack of high-quality datasets, fisheye camera distortion, and human body self-occlusion.
We propose a novel approach that leverages FisheyeViT to extract fisheye image features, which are converted into pixel-aligned 3D heatmap representations for 3D human body pose prediction.
arXiv Detail & Related papers (2023-11-28T07:13:47Z) - Towards Hard-pose Virtual Try-on via 3D-aware Global Correspondence
Learning [70.75369367311897]
3D-aware global correspondences are reliable flows that jointly encode global semantic correlations, local deformations, and geometric priors of 3D human bodies.
An adversarial generator takes the garment warped by the 3D-aware flow, and the image of the target person as inputs, to synthesize the photo-realistic try-on result.
arXiv Detail & Related papers (2022-11-25T12:16:21Z) - DRaCoN -- Differentiable Rasterization Conditioned Neural Radiance
Fields for Articulated Avatars [92.37436369781692]
We present DRaCoN, a framework for learning full-body volumetric avatars.
It exploits the advantages of both the 2D and 3D neural rendering techniques.
Experiments on the challenging ZJU-MoCap and Human3.6M datasets indicate that DRaCoN outperforms state-of-the-art methods.
arXiv Detail & Related papers (2022-03-29T17:59:15Z)
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.