Bundle Adjusted Gaussian Avatars Deblurring
This addresses a practical limitation in 3D avatar creation for applications like VR/AR, where sharp reference images are often unavailable due to human motion.
The paper tackles the problem of creating sharp 3D human avatars from blurry multi-view videos, which is challenging due to motion blur in real-world settings. Their method achieves state-of-the-art performance on both synthetic and real-captured datasets, surpassing existing baselines.
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.